Google Antigravity SignalsBack to the read

Every source behind the read

Every source GILD analyzed, newest first. Each says who the source is, how it knows, whether it still applies and which findings it counts toward. Open a count to see only its sources.

Source

140 sources in All practitioners, with product documentation Showing all 140 sources

Negative
SuneraX, Antigravity user
Antigravity agent stuck in endless file-reading loop (Gemini models)Forum post
With Gemini 3.7 Flash the agent loops re-reading the same files for hours, while Claude Sonnet 4.6 in Antigravity finished the same task in two minutes.
Published Oct 12, 2026self-described: App development
Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly; Observed on Gemini 3.7 Flash; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-10-12, Gemini 3.7 Flash
Counts toward
Reliability, run stability: unfavorable, G2 (2 units before bounds), capped: C-relationship
Not counted
Reliability, regressions: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity, Gemini 3.7 Flash and Claude Sonnet 4.6
Negative
Hans, runs a team's AI agents on its own server
Antigravity CLI: Workspace and Google AI Pro accounts are practically unusableForum post
Hans's team made about 55 calls over six days across five accounts; Workspace seats got the starter quota and a Pro account locked for 51 hours after five calls.
Published Oct 12, 2026self-described: Daily operations with several AI agents on a company server
Practitioner account, pseudonymous; ran the rollout; counts toward Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Ran the rollout; Specific details; Observed on Google AI Pro
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran the rollout
Support
No artifact or independent corroboration recorded
Date and version
2026-10-12, Google AI Pro
Counts toward
Cost predictability and limits, cost transparency: unfavorable, G2 (2 units before bounds), capped: C-relationship
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Cost predictability and limits, cost predictability: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Very small team
Evidence
Measured
Applies to
Current
Observed on
Antigravity CLI, Google Workspace and Google AI Pro
Positive
joaoviniciusgs, Hacker News commenter
Comment on: I made an open-source Boom 3D clone. Wanna check it out?Hacker News comment
joaoviniciusgs built an open-source Rust and Tauri audio app with Antigravity and Gemini 3.8 Flash, using the BMAD framework to plan, and was surprised how far structure took the model.
Published Oct 12, 2026self-described: Solo open-source Rust and Tauri app
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Gemini 3.8 Flash
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-10-12, Gemini 3.8 Flash
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity, Gemini 3.8 Flash
Positive
georgemcbay, Long-time OpenSCAD user
Comment on: OpenSCAD the Programmers Solid 3D CAD ModellerHacker News comment
georgemcbay finds Gemini with agy the best of the agents they have tried at OpenSCAD edits such as parametric fillets, while advising against one-shotting complex geometry.
Published Oct 10, 2026self-described: Hobby CAD
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-10-10
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
tinyhouse, Hacker News commenter, former Pro subscriber
Comment on: Gemini 4 ArgonHacker News comment
A week with Antigravity and the latest Gemini model was the worst of more than five harness and model pairs tinyhouse tried, and they canceled Pro.
Published Oct 1, 2026self-described: Compared more than five harnesses
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-10-01
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- How does Antigravity compare with the other coding agents engineers use?: Behind
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
mapontosevenths, Hacker News commenter, Google AI Ultra subscriber
Comment on: Gemini 4 ArgonHacker News comment
mapontosevenths finds agy better than Gemini CLI but behind Claude Code and Codex: no piping from standard input, hard iteration limits, frequent API errors and general instability.
Published Oct 1, 2026self-described: Terminal workflows
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-10-01
Not counted
Reliability, service availability: repeats a stronger account in its group
Not counted
Reliability, run stability: repeats a stronger account in its group
Not counted
Operational control, execution control: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Google AI Ultra
Positive
taylorfinley, Hacker News commenter
Comment on: Gemini 4 ArgonHacker News comment
Given an error message, agy with Gemini 3.8 Flash attached GDB to their GPU driver, reverse-engineered the ioctl interface and wrote a working LD_PRELOAD shim.
Published Sep 30, 2026self-described: Personal local-model setup
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini 3.8 flash
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
1 artifact (repository)
Date and version
2026-09-30, Gemini 3.8 flash
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Multi-Step Execution: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Gemini 3.8 Flash
Negative
smartbit, Hacker News commenter
Comment on: Gemini 4 ArgonHacker News comment
smartbit could not make agy sandbox mode workable, so they reluctantly run it with permissions skipped, and they miss Gemini CLI's pre-write diff tabs.
Published Sep 30, 2026self-described: Documentation and coding in the terminal
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini 3.8 flash
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-30, Gemini 3.8 flash
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds)
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Gemini 3.8 Flash
Positive
huydotnet, Hacker News commenter
Comment on: Gemini 4 ArgonHacker News comment
huydotnet plans with Opus 5.5 High and dispatches agy to do the work on Gemini Flash, and calls agy's usage limit very generous.
Published Sep 30, 2026self-described: Personal; Google AI Pro through their phone carrier
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Google AI Pro
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-30, Google AI Pro
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Google AI Pro, Opus 5.5 and Gemini Flash
Positive
martythemaniak, Hacker News commenter
Comment on: Gemini 4 ArgonHacker News comment
Over SSH, agy set up Docker, CUDA, ROS2 and Foxglove for their lidar on a Jetson and it all worked, using 6 percent of their weekly limit.
Published Sep 30, 2026self-described: Robotics hobby project
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-30
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Measured
Applies to
Current
Observed on
Antigravity CLI
Mixed
piyh, Hacker News commenter
Comment on: Gemini 4 ArgonHacker News comment
Finds the models fine and the limits generous but the developer experience far behind. Antigravity queues prompts while a long-running process is active, deleted the author's IDE during its move to a Codex clone, and hid usage limits for almost a year.
Published Sep 30, 2026self-described: Parallel work in worktrees
Practitioner account, pseudonymous; direct use; counts toward Reliability, Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-30
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds)
Counts toward
Reliability, regressions: unfavorable, G2 (2 units before bounds)
Counts toward
Cost predictability and limits, cost transparency: unfavorable, G2 (2 units before bounds)
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
Janson79jc, solo developer
Stress Test: 100% Antigravity + Gemini Flash, 102.8B tokens and 474K LOCTelemetry report (GitHub repository)
A solo developer reports 102.8 billion tokens and 474K lines of code across 465 Antigravity sessions with Gemini Flash, including two catastrophic collapses.
Published Sep 27, 2026self-described: Solo, 474K line codebase over 465 sessions
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes, Reliability, Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly; Specific details; Observed on Gemini 3.5 Flash; Gemini 3.6 Flash
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-27, Gemini 3.5 Flash; Gemini 3.6 Flash
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Delivered outcomes, context handling: mixed, G2 (2 units before bounds), capped: C-relationship
Counts toward
Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Reliability, run stability: unfavorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Measured
Applies to
Current
Observed on
Antigravity, Gemini Flash series
Positive
parasti, Hacker News commenter
Comment on: Plan mode is deadHacker News comment
On hobby projects parasti starts Antigravity CLI with /plan, reviews and approves the plan artifact, then finds implementation much faster than Claude.
Published Sep 26, 2026self-described: Hobby projects; Claude Code at work
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-26
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI
Negative
Freya Smith, uses Antigravity for work
Severe slowdowns and frequent 503 errors on Gemini Flash 3.8 during specific hoursForum post
Using Antigravity for work in the evening UTC, Freya Smith sees frequent 503 no-capacity errors and Flash slowing to a tenth of its usual speed.
Published Sep 25, 2026self-described: Daily work between 16:00 and 22:00 UTC
Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly; Artifact checked (log); Observed on gemini-3.8-flash-high
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
1 artifact (log)
Date and version
2026-09-25, gemini-3.8-flash-high
Counts toward
Reliability, service availability: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Reliability: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity, Gemini 3.8 Flash
Negative
flying_manta, Antigravity CLI user
Problem with antigravity CLI using shell commands for everythingForum post
flying_manta's CLI edits files with sed, bypassing native tools and breaking /rewind. It ignores an AGENTS.md rule telling it to stop.
Published Sep 23, 2026self-described: Daily CLI use
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-23
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Reliability: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI
Mixed
Dhruv Jani, developer
We All Have a "Serious Work" AI and a "Just Vibing" AI. When Did That Happen?Personal blog post, dev.to
Dhruv Jani uses Claude Opus in Antigravity for planning and hard bugs and Gemini 3.1 Pro for routine work because of headroom, though Gemini hallucinates more; a browser check looped on screenshots.
Published Sep 22, 2026self-described: Daily IDE work
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability, Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Gemini 3.1 Pro; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-22, Gemini 3.1 Pro
Counts toward
Delivered outcomes, correctness: unfavorable, G1 (1 unit before bounds)
Counts toward
Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relevance
Counts toward
Operational control, models and deployment: favorable, G1 (1 unit before bounds)
Counts toward
Cost predictability and limits, limits in practice: mixed, G1 (1 unit before bounds), capped: C-relevance
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
dlahoda, Engineer running a review orchestration on their team's repository
Comment on: GPT-5.6 Luna vs. GPT-6 Astra: Is a US$1.20 Model Good Enough for Code Review?Hacker News comment
dlahoda's review orchestration uses an agy US$200 plan as a second opinion for eliminating false positives, alongside GPT-6 Astra.
Published Sep 14, 2026self-described: Team repository with several review bots
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on agy 200usd sub
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-14, agy 200usd sub
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Is Antigravity the team's main coding tool, or one beside another?: Second tool
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Google AI Ultra
Positive
vallerie, Hacker News commenter
Comment on: Ask HN: What default model do you use and why?Hacker News comment
With detailed plans and test harnesses, vallerie gets good results from the Gemini Flash family in Antigravity, mainly for speed three to four times faster than competitors.
Published Sep 12, 2026self-described: Plan and test-harness driven work
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on 3.X Flash family
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-12, 3.X Flash family
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
evilduck, Hacker News commenter
Comment on: Benchmark: CadQuery vs. OpenSCAD for agentic CAD workHacker News comment
Had Gemini 3.8 Flash in Antigravity swap a fan shroud design into an existing STL of a computer case front plate. It made 2D renders from each axis, which the author takes to be for its own visual check, then wrote a Python program that manipulated the STL geometries, and it went perfectly.
Published Sep 12, 2026self-described: Home and hobbyist CAD for 3D printing
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini 3.8 Flash
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-12, Gemini 3.8 Flash
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Multi-Step Execution: Positive
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity, Gemini 3.8 Flash
Negative
rafaelmn, Hacker News commenter
Comment on: GPT-6 AstraHacker News comment
Tried Gemini Flash in Antigravity on a long-shelved side project: insanely fast, but its code was drivel worth throwing away. Astra on the same problem was sluggish in comparison, yet its pushback was meaningful and it could be steered.
Published Sep 5, 2026self-described: Long-planned side project
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Gemini Flash 3.8
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-05, Gemini Flash 3.8
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity, Gemini 3.8 Flash
Positive
allthetime, Hacker News commenter
Comment on: Gemini 3.8 Flash and 3.8 Flash CyberHacker News comment
allthetime now uses Antigravity as their main tool at work with all their company's services in one project, planning with the agents before letting them run across service boundaries.
Published Sep 3, 2026self-described: Company codebase: web, React Native, CMS, ETL and websocket services
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-03
Counts toward
Delivered outcomes, context handling: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Current
Negative
Gergely Orosz, author of The Pragmatic Engineer
Antigravity's terms of service and third-party useX post
Read Antigravity's terms as letting Google suspend a whole Google account it suspects of third-party use, such as running OpenClaw, and declined to use Antigravity because of that risk.
"…if they determine you use Antigravity in a way they suspect is eg third-party usage (eg use OpenClaw), they can suspend your Google account."
Excerpt, Gergely Orosz
Published Sep 3, 2026self-described: Writes about engineering teams and their tooling; deciding whether to use Antigravity himself
Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, author profile, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-09-03
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Data Privacy: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Positive
dpweb, Hacker News commenter, student plan
Comment on: Google Antigravity introduces Boost deep reasoning (/boost)Hacker News comment
On a student Google AI Pro plan dpweb likes the weekly allowance and Flash 3.7, bought extra credits, and uses agy for devops such as SSH servers on their home network.
Published Sep 1, 2026self-described: Personal devops and home network
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Observed on Flash 3.7 high
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-01, Flash 3.7 high
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Gemini 3.7 Flash, Google AI Pro student
Positive
sanarothe, Non-software engineer
Comment on: Google Antigravity introduces Boost deep reasoning (/boost)Hacker News comment
sanarothe finds Antigravity completes assigned tasks by following the agreed plan, sometimes with parallel subagents, and has not hit limits.
Published Sep 1, 2026self-described: Personal projects on a personal plan
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-01
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
dan_voronov, Blogger reviewing AI programming tools
Comment on: Google Antigravity introduces Boost deep reasoning (/boost)Hacker News comment
dan_voronov found the desktop app nearly unusable and used the CLI until switching harnesses; Google's limits are barely noticeable, but Flash trails Sol in quality.
Published Sep 1, 2026self-described: Long-term testing of Antigravity 1 and 2
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Observed on Antigravity 1 and 2
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed); customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-01, Antigravity 1 and 2
Not counted
Reliability, run stability: repeats a stronger account in its group
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
leoedin, Hacker News commenter, former subscriber
Comment on: Google Antigravity introduces Boost deep reasoning (/boost)Hacker News comment
leoedin canceled after Google applied lower limits retroactively, which put the account over them after days without use.
Published Sep 1, 2026self-described: Personal use
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-09-01
Not counted
Cost predictability and limits, cost predictability: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Quotas & Plan Changes: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Mixed
hn_throw2025, Hacker News commenter, former Cursor subscriber
Comment on: Our decision on Cursor following its acquisition by SpaceXHacker News comment
After canceling Cursor hn_throw2025 tried Antigravity IDE v1, doubts it will last, prefers its hunk review to the VS Code extension, and reviews diffs in Antigravity 2.0 beside JetBrains.
Published Aug 29, 2026self-described: Uses Antigravity 2.0 beside a JetBrains IDE
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Antigravity IDE v1; Google Antigravity2
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-29, Antigravity IDE v1; Google Antigravity2
Counts toward
Operational control, execution control: favorable, G2 (2 units before bounds)
Not counted
Adoption and upkeep, continuity: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity IDE, Antigravity 2.0, VS Code extension
Positive
slaser79, Hacker News commenter
Comment on: Why does Opus 5 feel worse to work with?Hacker News comment
slaser79 now spreads work across models and finds Gemini Flash in Antigravity underrated and fast for small and medium changes.
Published Aug 14, 2026self-described: Holds Anthropic, OpenAI and Google subscriptions
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on gemini flash
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-14, gemini flash
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
Jesus Padilla Soqui, Straiker STAR team
Nothing to See Here: How an AI Agent Buried Its Own CommandsSecurity research write-up, Straiker blog
Padilla Soqui of Straiker shows an email disguised as a routine company backup request leading an Antigravity-connected agent to collect SSH and PEM keys and upload them, while the approval dialog showed only a script name. Google categorized the report as a duplicate.
"The confirmation dialog, the last line of defense in most agent architectures, exposed only a script name and never the commands, the destination, or the files involved."
Excerpt, Jesus Padilla Soqui
Published Aug 14, 2026self-described: Agentic AI security company assessing the Antigravity platform
Practitioner account, self-described; structured test; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2026-08-14
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Permissions & Safety: Raised as a concern
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Reported
Applies to
Current
Observed on
Antigravity agent connected to email
Mixed
Tanaike, Google Developer Expert
Preventing Quota Crashes via Antigravity CLI Agent HooksPersonal blog post, dev.to (Google Developer Experts)
Tanaike describes Antigravity CLI users on Google OAuth hitting abrupt task failures when quota reaches 0%, and an invalid thought signature error in CLI v1.1.12 when resuming a session after switching accounts. Built a hook plugin that warns before quota runs out, using no model tokens.
Published Aug 12, 2026self-described: Autonomous Antigravity CLI sessions
Practitioner account, self-described; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Google Antigravity partner: not counted as independent; Used it directly; Artifact checked (log); Observed on Antigravity CLI v1.1.12
Role
Name self-described; employer unknown; role unknown
Relationship
program member (suspected)
How they know
Used it directly
Support
2 artifacts (log)
Date and version
2026-08-12, Antigravity CLI v1.1.12
Counts toward
Reliability, service availability: unfavorable, G3 (3 units before bounds)
Counts toward
Reliability, run stability: unfavorable, G3 (3 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Not counted
Its author is a Google Developer Expert, a program Google runs. Kept in the record; it takes part in no figure.
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI 1.1.12
Negative
qlte, Hacker News commenter, Google AI Pro subscriber
Comment on: Discovery LoopHacker News comment
After the Gemini CLI shutdown qlte could not make Antigravity CLI work on Pro quotas without instant rate limits and moved to Codex and OpenCode Go.
Published Aug 5, 2026self-described: Personal use after the Gemini CLI shutdown
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Pro plan
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-08-05, Pro plan
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Quotas & Plan Changes: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Google AI Pro
Positive
malkamius, Hacker News commenter
Comment on: So what is your programming setup? Hype is making fundamentals confusingHacker News comment
malkamius runs Antigravity in turbo mode with no restrictions inside a restorable Ubuntu VM, hardly reads the code, and tests each release by hand.
Published Jul 27, 2026self-described: Hobby game add-ons, run in a VM
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-27
Counts toward
Operational control, execution control: favorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
dudeinhawaii, Hacker News commenter, former Google AI Ultra subscriber
Comment on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash CyberHacker News comment
Across many experiments Gemini in Antigravity went off track far more than Codex or Claude Code, and dudeinhawaii canceled Ultra.
Published Jul 22, 2026self-described: Daily use of several providers
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Observed on 2.5, 3, 3.1, 3.5; Ultra plan
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-22, 2.5, 3, 3.1, 3.5; Ultra plan
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
tobias2014, Hacker News commenter
Comment on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash CyberHacker News comment
Forced early compaction in Antigravity makes Gemini forget and cut corners even with a rigorous GEMINI.md and task tracking, so tobias2014 finds it useless for complex autonomous work.
Published Jul 22, 2026self-described: Complex problems, run semi-autonomously
Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on 3.1-pro, flash 3.6; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-22, 3.1-pro, flash 3.6
Counts toward
Reliability, run stability: unfavorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity, Gemini 3.1 Pro and 3.6 Flash
Negative
stonewhite, Hacker News commenter buying AI tools for their company
Comment on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash CyberHacker News comment
Google ending the Ultra subscription pushed their company off Antigravity; Gemini Enterprise Agent Platform setup was hard and per-user spend limits needed a project per user.
Published Jul 21, 2026self-described: Company that standardized on Google AI Ultra
Practitioner account, pseudonymous; ran the rollout; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Ran the rollout; Specific details; Observed on AI Ultra subscription
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed); customer (self disclosed); customer (self disclosed)
How they know
Ran the rollout
Support
No artifact or independent corroboration recorded
Date and version
2026-07-21, AI Ultra subscription
Counts toward
Adoption and upkeep, continuity: unfavorable, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Needs a recheck
Positive
mythz, Hacker News commenter
Comment on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash CyberHacker News comment
mythz calls the annual Antigravity Pro plan at US$16.67 a month the best plan available and uses Antigravity IDE as their workhorse, with Claude Pro for Opus.
Published Jul 21, 2026self-described: Solo, full-time development
Practitioner account, pseudonymous; direct use; counts toward Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Specific details; Observed on Antigravity Pro 16.67/mo plan (Annual)
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed); customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-21, Antigravity Pro 16.67/mo plan (Annual)
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Google AI Pro annual, Antigravity IDE
Negative
mwryl, Hacker News commenter
Comment on: Kimi K3, Qwen 3.8, and Anthropic's (Potential) UnravellingHacker News comment
mwryl's team replaced Antigravity with Claude, GPT, and Kimi models for development, and builds its own systems around cheaper models.
Published Jul 20, 2026self-described: Team building products on low-cost models; replaced Antigravity for development
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-20
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- How does Antigravity compare with the other coding agents engineers use?: Behind
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Current
Positive
Rohan Soni, Google, writing Inspired Entertainment's case study with its CTO
Trusted automation with Google Antigravity: Scaling secure finance integrations from 40 Days to 5Vendor case study, Google Developer forums
In a Google case study, Inspired Entertainment says agent-generated adapters cut builds from 6 to 8 weeks to 1 week and 40 dev days to 5. It now names Antigravity CLI as its core engine.
Published Jul 20, 2026self-described: Integration team building Java Spring Boot wallet adapters
Vendor material, pseudonymous; ran the rollout; not counted, tied to the vendor How GILD checked it
Origin
Vendor material
Checked
Pseudonymous; Google Antigravity partner: not counted as independent; Ran the rollout; Specific details; Observed on Gemini CLI
Role
Pseudonymous account; identity not pursued
Relationship
vendor published (suspected); partner (self disclosed)
How they know
Ran the rollout
Support
No artifact or independent corroboration recorded
Date and version
2026-07-20, Gemini CLI
Not counted
Delivered outcomes, task completion: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Delivered outcomes, correctness: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Delivered outcomes, context handling: excluded, praise from someone tied to the vendor, kept as an attributed position
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Not counted
Google wrote and published this case study. Kept in the record; it takes part in no figure.
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Measured
Applies to
Current
Observed on
Gemini CLI, now Antigravity CLI
Negative
Dan Lisichkin, security researcher at Pillar Security
The Week of Sandbox Escapes Day 1: Escaping Antigravity's Allow-Default SeatbeltSecurity research write-up, Pillar Security blog
Read the macOS sandbox profile in Antigravity build 1.15.8 and found it starts from allow default, so anything missing from its denylist is permitted. The team mounted a devfs volume and used Launch Services to start code outside the sandbox.
"Antigravity went with (allow default). That single line at the top of the profile converts it to a denylist which predicts most of what follows."
Excerpt, Dan Lisichkin
Published Jul 20, 2026Pillar Research team testing agentic IDE sandboxes on macOS
Practitioner account, self-described; structured test; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Specific details; Observed on build 1.15.8
Role
Name self-described; employer self-described; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2026-07-20, build 1.15.8
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Permissions & Safety: Raised as a concern
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Reported
Applies to
Current
Observed on
Antigravity build 1.15.8 macOS sandbox profile
Positive
Andrey Lukyanenko, ML engineer and Google Developer Expert
Starting and iterating on a Kaggle competition in Google AntigravityPersonal blog post, andlukyane.com
Andrey Lukyanenko ran a Kaggle competition in Antigravity 2.0 from a starter kit of rules, a fixed fold split and an experiment log, and stresses constraints and validation checks.
Published Jul 9, 2026self-described: Kaggle Playground competition
Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Google Antigravity partner: not counted as independent; Used it directly; Specific details; Observed on Google Antigravity 2.0 with Gemini 3.1 Pro
Role
Name self-described; employer unknown; role unknown
Relationship
program member (suspected); program member (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-09, Google Antigravity 2.0 with Gemini 3.1 Pro
Counts toward
Delivered outcomes, task completion: mixed, G2 (2 units before bounds), capped: C-relationship
Counts toward
Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Not counted
Its author is a Google Developer Expert, a program Google runs. Kept in the record; it takes part in no figure.
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity 2.0, Gemini 3.1 Pro
Negative
SwellJoe, Developer building a security auditing harness
Comment on: The classifiers Anthropic puts in front of Fable are too zealousHacker News comment
In security benchmarking work SwellJoe found Gemini in Antigravity refuses any security auditing task, even a plain request to find security bugs.
Published Jul 8, 2026self-described: Security auditing harness and benchmarks
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-08
Counts toward
Delivered outcomes, task completion: unfavorable, G2 (2 units before bounds)
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Reliability: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
Christopher Tuz, AI security researcher on the STAR Labs team at Straiker
Ghostfabric: How An AI Coding Agent Was Tricked Into Exfiltrating Data Over VXLANSecurity research write-up, Straiker blog
Tuz of Straiker STAR Labs reports that Antigravity on Gemini 3.1 Pro, asked to take care of a home-automation project shared over Google Drive, ran a compiled file after the agent checked only that its CPU architecture matched the test machine, which the author calls "the entire security review"; the file sent the Documents folder out over VXLAN. Google categorized it as prompt injection.
"Before running anything, Antigravity performed exactly one piece of due diligence: it confirmed the compiled file's CPU architecture matched the test machine. That was the entire security review."
Excerpt, Christopher Tuz
Published Jul 8, 2026Agentic AI security company red teaming coding agents
Practitioner account, name and role on their organization's own page; structured test; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Name and role on their organization's own page; Ran a structured test; Specific details; Observed on Gemini 3.1 Pro
Role
Name on a page the person does not control; employer on a page the person does not control; role on a page the person does not control (Christopher Tuz is an AI security researcher on Straiker's STAR Labs team)
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2026-07-08, Gemini 3.1 Pro
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Reported
Applies to
Current
Observed on
Antigravity agent on Gemini 3.1 Pro
Mixed
yogendra6698, Builds AI agents professionally
Comment on: I'm opening VSCode less and less every dayHacker News comment
Antigravity writes 60 to 65 percent of their code, but once 2.0 separated the agent manager from the IDE yogendra6698 went back to VS Code as their primary editor.
Published Jul 3, 2026self-described: Daily development
Practitioner account, pseudonymous; direct use; not counted, tied to the vendor How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Google Antigravity staff: not counted as independent; Used it directly; Observed on Antigravity 2.0; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
vendor employee (suspected)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-07-03, Antigravity 2.0
Not counted
Delivered outcomes, task completion: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Adoption and upkeep, continuity: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Not counted
Its author is an AI engineer at Google Cloud, and Google makes Antigravity. Kept in the record; it takes part in no figure.
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
moshegramovsky, Hacker News commenter
Comment on: Google limits Meta's use of its Gemini AI modelsHacker News comment
Recent sessions brought broken code insertion, lost chat history and wasteful searches, so moshegramovsky now uses Antigravity for planning and hands coding to Codex.
Published Jun 28, 2026self-described: Personal C++ development
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-28
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Not counted
Reliability, run stability: repeats a stronger account in its group
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Adoption and upkeep, continuity: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
anigbrowl, Hacker News commenter
Comment on: Computer use in Gemini 3.5 FlashHacker News comment
The Antigravity app stopped partway through an agentic task to ask for a subscription and would not use the Gemini API credits anigbrowl had prepaid, so they switched tools.
Published Jun 25, 2026self-described: New paying Gemini API customer
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-25
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Cost predictability and limits, cost transparency: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
trollbridge, Hacker News commenter running a small development shop
Comment on: AI's Affordability CrisisHacker News comment
Uses Antigravity when working on Android or Google Cloud API codebases. At the author's development shop, the author is the only Codex user, everyone gets OpenCode Go, and the shop also pays for DeepSeek and MiMo and runs Qwen models locally.
Published Jun 23, 2026self-described: Small shop that competes with offshore development firms
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-23
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Is Antigravity the team's main coding tool, or one beside another?: Second tool
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Current
Positive
linsomniac, Hacker News commenter
Comment on: The text in Claude Code's "Extended Thinking" outputHacker News comment
linsomniac has Codex and Antigravity review each specification, implementation guide and checklist and work to consensus, and finds Opus plus that review loop strong.
Published Jun 22, 2026self-described: Spec-first workflow across agents
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-22
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
bjackman, Hacker News commenter
Comment on: John Jumper to join AnthropicHacker News comment
bjackman rates Antigravity CLI a big step up from Gemini CLI with real advantages over Claude Code, but moved to Claude because the Gemini model hallucinates and ignores instructions.
Published Jun 20, 2026self-described: Personal use of Gemini and Claude
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-20
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Gemini models
Mixed
polotics, Hacker News commenter
Comment on: Running local models is good nowHacker News comment
Running the same prompt in two branches, polotics found Antigravity with Gemini 3.5 smarter than a local model but prone to time and token consuming tangents.
Published Jun 16, 2026self-described: Solo Android app, about 10,000 lines of Kotlin
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini3.5
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-16, Gemini3.5
Counts toward
Delivered outcomes, task completion: unfavorable, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity, Gemini 3.5
Positive
evilturnip, Hacker News commenter
Comment on: DiffusionGemma: 4x Faster Text GenerationHacker News comment
Switching personal projects to Antigravity with Flash models kept them in flow; evilturnip still prefers Claude for very complex, large codebases.
Published Jun 10, 2026self-described: Personal projects
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Flash models
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-06-10, Flash models
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity, Gemini Flash
Negative
seabrookmx, Hacker News commenter
Comment on: Microsoft starts canceling Claude Code licensesHacker News comment
Faced with moving from Code Assist and Gemini CLI to Antigravity, reinstalling tooling and a clunkier Cloud subscription, their team moved to Claude instead.
Published May 23, 2026self-described: Team at a large Google Cloud customer
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-05-23
Not counted
Adoption and upkeep, continuity: repeats a stronger account in its group
Not counted
Adoption and upkeep, setup: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Product Direction: Raised as a concern
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Needs a recheck
Mixed
mark_l_watson, Retired developer and author
Comment on: Google's Antigravity bait and switchHacker News comment
Installing the new Antigravity, the IDE and the CLI took 90 minutes. In their Ultra test, Antigravity with Claude Opus finished tasks in 60 to 70 percent of the time of cheaper open models.
Published May 22, 2026self-described: One-month Google AI Ultra test
Practitioner account, pseudonymous; structured test; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Ran a structured test; Specific details; Observed on Gemini Ultra
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2026-05-22, Gemini Ultra
Counts toward
Adoption and upkeep, setup: unfavorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Measured
Applies to
Current
Observed on
Google AI Ultra, Claude Opus
Negative
heyyeah, Hacker News commenter
Comment on: Google's Antigravity bait and switchHacker News comment
Finishing the Antigravity IDE install required agreeing to let Google collect their interactions data; heyyeah filed a bug and looked for the opt-out.
Published May 22, 2026self-described: Installing Antigravity IDE after 2.0
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-22
Counts toward
Operational control, data control: unfavorable, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Data Privacy: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity IDE installer
Negative
u8, Developer of CLI developer tooling
Comment on: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM BenchmarkHacker News comment
In daily use the Antigravity CLI TUI garbles input during output, lacks mode-switch shortcuts, and scaffolding a simple Deno site used their five-hour limit.
Published May 22, 2026self-described: Personal site build
Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-22
Counts toward
Reliability, run stability: unfavorable, G2 (2 units before bounds)
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI
Negative
daft_pink, Hacker News commenter
Comment on: Google's Antigravity Bait and SwitchHacker News comment
daft_pink canceled Workspace Ultra and moved to a personal Ultra plan to keep Antigravity, while keeping Gemini chat on Workspace because the individual plan lacks full privacy.
Published May 21, 2026self-described: Workspace user
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Observed on personal developer ultra plan
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-21, personal developer ultra plan
Not counted
Operational control, data control: repeats a stronger account in its group
Not counted
Adoption and upkeep, continuity: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Mixed
spankalee, Hacker News commenter
Comment on: Google's Antigravity Bait and SwitchHacker News comment
The update replaced their app with the 2.0 conversation UI without warning; the IDE was still installed, and one prompt to choose an app would have avoided the confusion.
Published May 21, 2026self-described: Existing Antigravity user
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-21
Not counted
Adoption and upkeep, continuity: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Product Direction: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity 2.0 update
Mixed
Joske Vermeulen, runs an autonomous agent startup race
My AI Agent Hit Google's Quota Wall in 8 Minutes. 36 Hours Later, Google Tripled the Limits.Personal blog post, dev.to
Joske Vermeulen's autonomous agent on Antigravity CLI fixed 32 broken files in one commit but hit the five-hour wall after 8 minutes, about 68 minutes a week, before Google tripled limits.
Published May 21, 2026self-described: Autonomous agent on cron, US$20 Pro plan
Practitioner account, self-described; structured test; counts toward Delivered outcomes, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Google Antigravity found in GILD's check; Ran a structured test; Specific details; Observed on Gemini 3.5 Flash
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2026-05-21, Gemini 3.5 Flash
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, correctness: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, context handling: favorable, G2 (2 units before bounds)
Counts toward
Cost predictability and limits, limits in practice: mixed, G1 (1 unit before bounds), capped: C-relevance
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Measured
Applies to
Current
Observed on
Antigravity CLI, Gemini 3.5 Flash, Google AI Pro
Negative
Jason Agostoni, developer and author of the Ship Bench benchmark
Antigravity CLI First Impressions: Fast, Rough, and Not ReadyPersonal blog post, dev.to
On Ship Bench the CLI forgot approved permissions, hung on Windows, and hit quota within two iterations while showing 20 percent left; Claude Code finished seven.
Published May 21, 2026self-described: Ship Bench run on Windows
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability, Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini 3.5 Flash
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-21, Gemini 3.5 Flash
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds)
Counts toward
Reliability, run stability: unfavorable, G1 (1 unit before bounds)
Counts toward
Delivered outcomes, correctness: unfavorable, G1 (1 unit before bounds)
Counts toward
Cost predictability and limits, limits in practice: unfavorable, G1 (1 unit before bounds), capped: C-relevance
Counts toward
Cost predictability and limits, cost predictability: unfavorable, G1 (1 unit before bounds), capped: C-relevance
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Measured
Applies to
Current
Observed on
Antigravity CLI, Gemini 3.5 Flash, Google AI Pro
Positive
ModelRift engineering team
OpenSCAD LLM Benchmark: Building the PantheonCompany benchmark post, ModelRift blog
In the team's OpenSCAD Pantheon benchmark, Antigravity 2.0 with Gemini 3.5 Flash High scored 4.5 of 5 for quality, the best autonomous result, but 1 of 5 for speed.
Published May 21, 2026self-described: Company benchmarking coding agents for its OpenSCAD product
Practitioner account; structured test; not counted, tied to the vendor How GILD checked it
Origin
Published practitioner account
Checked
Competitor staff: not counted as independent; Ran a structured test; Artifact checked (benchmark output); Observed on Google Antigravity 2.0 / Gemini 3.5 Flash High
Role
Name unknown; employer unknown; role unknown
Relationship
competitor employee (self disclosed)
How they know
Ran a structured test
Support
1 artifact (benchmark output)
Date and version
2026-05-21, Google Antigravity 2.0 / Gemini 3.5 Flash High
Not counted
Delivered outcomes, measured outcomes: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Adoption and upkeep, continuity: excluded, criticism from a competitor's side, kept as an attributed position
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Measured
Applies to
Current
Observed on
Antigravity 2.0, Gemini 3.5 Flash High
Negative
Sid, independent developer on Google AI Ultra
Google's Antigravity Bait and SwitchPersonal blog post, Sid's Blog
The 2.0 update replaced their IDE with a chat app, the legacy installer kept launching 2.0 until Sid purged everything, and their history and settings were lost.
Published May 21, 2026self-described: Daily production work
Practitioner account; direct use; counts toward Reliability, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Customer of Google Antigravity; Used it directly; Specific details; Observed on 2.0
Role
Name unknown; employer unknown; role unknown
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-21, 2.0
Counts toward
Reliability, regressions: unfavorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Adoption and upkeep, continuity: unfavorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Adoption and upkeep, ongoing upkeep: unfavorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Google AI Ultra, Antigravity IDE then 2.0
Negative
Madhur Mishra, Antigravity user
Recent Antigravity Changes Have Seriously Hurt the ExperienceForum post
Madhur Mishra finds the May changes cut usable limits and split the same-screen editor and agent workflow they valued most.
Published May 20, 2026self-described: Daily development
Practitioner account, pseudonymous; direct use; counts toward Operational control, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-20
Counts toward
Cost predictability and limits, limits in practice: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Counts toward
Operational control, models and deployment: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Adoption and upkeep, continuity: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Mixed
MisterPea, Hacker News commenter
Comment on: Gemini CLI will stop working from June 18, 2026Hacker News comment
MisterPea finds Antigravity CLI better than Gemini CLI, but Google's new single quota ends the separate allowances they had used across Gemini CLI, Antigravity and AI Studio.
Published May 20, 2026self-described: Personal use across Google tools
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-20
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI
Negative
No1, Hacker News commenter
Comment on: Gemini CLI will stop working from June 18, 2026Hacker News comment
On first use the built-in sandbox allowed network access without DNS, so No1 went sandboxless; their five-hour window then turned into a drained one-week window.
Published May 20, 2026self-described: First trial
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-20
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds)
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
tegeek, Hacker News commenter
Comment on: Gemini CLI will stop working from June 18, 2026Hacker News comment
After four months on Antigravity with the Claude Code extension, the 2.0 update removed their VS Code extensions and the dev-process integration tegeek had built.
Published May 20, 2026self-described: Four months of daily use with Kiro and Claude Code
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-20
Not counted
Adoption and upkeep, continuity: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Product Direction: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity IDE, Gemini 3.1 Pro, then Antigravity 2.0
Negative
cft, Hacker News commenter, Google AI Pro subscriber
Comment on: Qwen3.7-Max: The Agent FrontierHacker News comment
cft canceled Google AI Pro once Flash and Pro shared one quota, leaving four to five hours of Flash a week, and rates 3.1 Pro below Codex and Opus.
Published May 20, 2026self-described: Personal; Flash for auxiliary tasks
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Observed on Flash 3.5; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-20, Flash 3.5
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Google AI Pro, Gemini 3.5 Flash
Negative
almog, Hacker News commenter, Google AI Pro subscriber
Comment on: Gemini CLI will stop working from June 18, 2026Hacker News comment
Two prompts in two short Antigravity CLI sessions on Gemini 3.5 Flash used their whole weekly Pro quota, and almog could not see their token usage.
Published May 20, 2026self-described: Personal firmware reverse engineering
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Gemini Flash 3.5; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-20, Gemini Flash 3.5
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Cost predictability and limits, cost transparency: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Gemini 3.5 Flash, Google AI Pro
Negative
Vicente Cortes, Google One Pro subscriber for over a year
I'm done with AntigravityForum post
Vicente Cortes is leaving Antigravity: the IDE kept erroring, 2.0 replaced it even when asked to keep it, and creating one AGENTS.md used the Gemini quota.
Published May 19, 2026self-described: Personal projects
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes, Reliability, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly; Observed on Google One Pro; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-19, Google One Pro
Counts toward
Adoption and upkeep, continuity: unfavorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Cost predictability and limits, limits in practice: unfavorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Negative
smnscu, Hacker News commenter
Comment on: Cursor Introduces Composer 2.5Hacker News comment
smnscu moved from Antigravity back to VS Code, porting their settings with an agent, and found the speed and stability incomparable.
Published May 19, 2026self-described: Personal development
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-19
Not counted
Reliability, run stability: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Negative
lern_too_spel, Hacker News commenter
Comment on: Gemini 3.5 FlashHacker News comment
A few iterations into a simple project in the new Antigravity CLI, lern_too_spel hit an individual quota with a seven-day reset.
Published May 19, 2026self-described: Personal account, small project
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini 3.5
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-19, Gemini 3.5
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Quotas & Plan Changes: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Current
Observed on
Antigravity CLI, Gemini 3.5 Flash, personal account
Negative
mcoliver, Hacker News commenter, Workspace administrator
Comment on: A History of IDEs at GoogleHacker News comment
After Google removed the AI Ultra plan for Workspace, got Antigravity working again through Code Assist, a GCP project and custom JSON. Even with plenty of Gemini quota in GCP, Antigravity soon reported the author out of quota for a week on a separate Antigravity tracker.
Published May 14, 2026self-described: Moving their organization off the Workspace AI Ultra add-on
Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-14
Counts toward
Adoption and upkeep, setup: unfavorable, G2 (2 units before bounds)
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Needs a recheck
Negative
jatora, Hacker News commenter
Comment on: AlphaEvolve: Gemini-powered coding agent scaling impact across fieldsHacker News comment
jatora finds Antigravity slow and buggy, its permissions not respected and its Agent Manager crash-prone, and sees access to Opus as its one advantage.
Published May 8, 2026self-described: Personal use of several agents
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Opus
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-05-08, Opus
Not counted
Operational control, execution control: repeats a stronger account in its group
Not counted
Reliability, run stability: repeats a stronger account in its group
Not counted
Adoption and upkeep, continuity: repeats a stronger account in its group
Not counted
Operational control, models and deployment: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
saidinesh5, Hacker News commenter
Comment on: Using coding assistance tools to revive projects you never were going to finishHacker News comment
Each weekend with Antigravity produced a usable project, from an ESP8266 water-heater timer to a work Chrome extension; one prompt fixed an async bug saidinesh5 had traced.
Published Apr 27, 2026self-described: Weekend home-automation projects
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-27
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, correctness: mixed, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Negative
jdw64, Hacker News commenter
Comment on: Google is building a Claude Code challenger, Sergey Brin is involvedHacker News comment
jdw64 finds Google's AI tools fragmented and inconsistently priced, with an Antigravity auto-accept bug left unfixed for weeks, and worries Google will abandon projects.
Published Apr 25, 2026self-described: Subscribes to several AI tools
Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2026-04-25
Not counted
Operational control, execution control: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Reliability: Raised as a concern
- Product Direction: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
mark_l_watson, Retired developer and author
Comment on: Claude Code to be removed from Anthropic's Pro plan?Hacker News comment
On Google's US$20 plan mark_l_watson gets about three half-hour Antigravity sessions a week with Claude models, with much higher limits on Gemini Pro.
Published Apr 22, 2026self-described: Personal open-source projects
not counted, repeats a stronger account How GILD checked it
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed); customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-22, Google's $20/month plan
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Google AI Pro, Claude and Gemini Pro models
Mixed
WarmWash, Hacker News commenter
Comment on: Our eighth generation TPUs: two chips for the agentic eraHacker News comment
Given the same tax documents, Codex was right first time; Antigravity finished in two minutes but missed one value until prompted. WarmWash uses it for small greenfield projects.
Published Apr 22, 2026self-described: Personal tax return test and small greenfield projects
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-22, Gemini
Counts toward
Delivered outcomes, task completion: mixed, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Measured
Applies to
Needs a recheck
Negative
Dan Lisichkin, security researcher at Pillar Security
Prompt Injection leads to RCE and Sandbox Escape in AntigravitySecurity research write-up, Pillar Security blog
Found that Antigravity's find_by_name tool passed unvalidated input to fd, so a prompt injection could run arbitrary code even in Secure Mode, its most restrictive setting. Google accepted the report and marked the bug fixed on Feb 28, 2026.
"Critically, this vulnerability bypasses Antigravity's Secure Mode, the product's most restrictive security configuration."
Excerpt, Dan Lisichkin
Published Apr 20, 2026Pillar Research team testing agentic IDEs for sandbox bypasses
Practitioner account, self-described; structured test; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Specific details
Role
Name self-described; employer self-described; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2026-04-20
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Permissions & Safety: Raised as a concern
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE in Secure Mode, find_by_name tool
Negative
Ill_indication, Freelance developer building for clients
Antigravity servers down for over 7 hours!Forum post
Relies on Antigravity to build for clients, but a high-traffic error kept the author from getting any work done for over 7 hours. Reverting versions, switching to IPv4, a fresh install and buying a new plan on a separate account did not help.
Published Apr 15, 2026self-described: Client work
Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-15
Counts toward
Reliability, service availability: unfavorable, G2 (2 units before bounds), capped: C-relationship
Not counted
Cost predictability and limits, cost transparency: a lead (G0), counts toward nothing until substantiated
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Reliability: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Mixed
Alexander Tyutin, automation practitioner
Using OpenCode as a fallback agent for AntigravityPersonal blog post, dev.to (Google Developer Group)
High-load errors made Antigravity unusable even on Gemini 3 Flash, so Alexander Tyutin ran their Antigravity workflows from OpenCode as a fallback.
Published Apr 15, 2026self-described: Daily delivery work
Practitioner account, self-described; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Google Antigravity partner: not counted as independent; Used it directly; Specific details; Observed on Gemini 3 Flash
Role
Name self-described; employer unknown; role unknown
Relationship
program member (suspected); program member (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-15, Gemini 3 Flash
Counts toward
Reliability, service availability: unfavorable, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Not counted
Its author co-organizes GDG Almaty, a Google Developer Groups community Google runs. Kept in the record; it takes part in no figure.
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
Achshar, Hacker News commenter, Google AI Ultra subscriber
Comment on: Pro Max 5x quota exhausted in 1.5 hours despite moderate usageHacker News comment
Achshar has not hit quota issues on Google AI Ultra and finds the Antigravity interface better for development work than Claude Code.
Published Apr 12, 2026self-described: Personal development
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Ultra
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-12, Ultra
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Google AI Ultra
Negative
rzkyif, Hacker News commenter, Google AI Pro subscriber
Comment on: Pro Max 5x quota exhausted in 1.5 hours despite moderate usageHacker News comment
Gemini 3.1 Pro could burn rzkyif's weekly Antigravity limit on Google AI Pro in one to two hours, while Flash produced buggy code, so they moved to Claude Max.
Published Apr 12, 2026self-described: Personal ~15k line codebase
Practitioner account, pseudonymous; direct use; not counted, earlier release How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Out of date (Google AI Pro); Specific details
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed); customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-12, Google AI Pro, out of date
Not counted
Cost predictability and limits, limits in practice: excluded, describes an earlier release or was retracted
Not counted
Delivered outcomes, correctness: excluded, describes an earlier release or was retracted
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward nothing current
Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Out of date
Observed on
Google AI Pro, Gemini 3.1 Pro and Gemini 3 Flash
Positive
asdfasgasdgasdg, Programmer of twenty years
Comment on: Pro Max 5x quota exhausted in 1.5 hours despite moderate usageHacker News comment
On the US$20 plan the Pro quota ran out in an hour, but Flash with plan mode and hardware-in-loop tests got their STM32 project done about three times faster.
Published Apr 12, 2026self-described: Personal embedded motor-control project
Practitioner account, pseudonymous; direct use; not counted, earlier release How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Out of date ($20/mo plan); Specific details
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-12, $20/mo plan, out of date
Not counted
Cost predictability and limits, limits in practice: excluded, describes an earlier release or was retracted
Not counted
Delivered outcomes, task completion: excluded, describes an earlier release or was retracted
Not counted
Delivered outcomes, correctness: excluded, describes an earlier release or was retracted
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward nothing current
Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Out of date
Observed on
Google AI Pro, Gemini Flash in plan mode
Positive
Alexander Tyutin, automation practitioner
Antigravity: My Approach to Deliver the Most Assured Value for the Least MoneyPersonal blog post, dev.to (Google Developer Group)
Alexander Tyutin keeps task plans and debt logs in the repository, passes strict system instructions on every run, and switches between high- and low-tier models to save tokens.
Published Apr 1, 2026self-described: Delivery workflow with quality gates
Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Google Antigravity partner: not counted as independent; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
program member (suspected)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-04-01
Counts toward
Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds)
Not counted
Operational control, models and deployment: excluded, praise from someone tied to the vendor, kept as an attributed position
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Not counted
Its author co-organizes GDG Almaty, a Google Developer Groups community Google runs. Kept in the record; it takes part in no figure.
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Negative
aaron_wu, Aaron Wu, long-time paying user
Google Antigravity: Secret Quota Cuts, Break Trust & Make It Unusable for ProductionForum post
After quiet Pro cuts aaron_wu moved to Ultra, but further unannounced cuts and weaker output left Antigravity, in their view, unfit for production work.
Published Mar 26, 2026self-described: Production work, upgraded from Pro to Ultra
Practitioner account, pseudonymous; direct use; counts toward Reliability, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Observed on Ultra
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-03-26, Ultra
Counts toward
Cost predictability and limits, limits in practice: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Reliability, service availability: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Not counted
Cost predictability and limits, cost predictability: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Google AI Ultra
Negative
Mariano Abad, Google AI Ultra subscriber
[Ultra] Dramatic quota reduction after update: this needs an official explanationForum post
On the Ultra tier, multiple agents running complex tasks for 5+ hours used to leave quota above 80%; after the update the same workflows hit 0% in under 90 minutes, which the author calls a 5x to 6x cut.
Published Mar 23, 2026self-described: Several agents running complex tasks in parallel
Practitioner account, pseudonymous; direct use; counts toward Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly; Observed on Ultra; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-03-23, Ultra
Counts toward
Cost predictability and limits, cost predictability: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Counts toward
Cost predictability and limits, cost transparency: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Measured
Applies to
Needs a recheck
Observed on
Google AI Ultra
Positive
Patricio Navarro, data engineer and Google Developer Expert
Testing Antigravity: Building a Data-Intensive POC at 300km/hPersonal blog post, dev.to (Google Developer Experts)
Building a Pub/Sub to BigQuery pipeline, Patricio Navarro moved fast but had to enforce idempotency and schema standards where the agent took happy-path shortcuts.
Published Mar 22, 2026self-described: GCP data pipeline prototype
Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Google Antigravity partner: not counted as independent; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
program member (suspected); program member (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-03-22
Counts toward
Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: excluded, praise from someone tied to the vendor, kept as an attributed position
Not counted
Delivered outcomes, context handling: excluded, praise from someone tied to the vendor, kept as an attributed position
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Not counted
Its author is a Google Developer Expert, a program Google runs. Kept in the record; it takes part in no figure.
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Negative
riversflow, Hacker News commenter, Google AI Pro subscriber
Comment on: Google Antigravity IDE rug pulls its quotasHacker News comment
After Google cut weekly quotas retroactively, riversflow found every quota but Gemini Flash at zero with a nearly five-day reset and considered moving to Claude Code.
Published Mar 11, 2026self-described: Personal building on a Pro subscription
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Pro subscription
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
1 artifact (organization page)
Date and version
2026-03-11, Pro subscription
Not counted
Cost predictability and limits, cost predictability: repeats a stronger account in its group
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Quotas & Plan Changes: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Google AI Pro
Positive
jpadkins, Hacker News commenter
Comment on: Agentic Engineering PatternsHacker News comment
jpadkins's loop: prompt the next change, check the implementation plan when it is large, play-test the previous batch while the agent works, then commit.
Published Mar 5, 2026self-described: Hobby game development
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-03-05
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Negative
maccard, Hacker News commenter
Comment on: Agentic Engineering PatternsHacker News comment
In two weeks of testing, Antigravity with Gemini regularly got stuck on simple issues and looped until their requests ran out.
Published Mar 4, 2026self-described: Personal evaluation
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-03-04
Not counted
Reliability, run stability: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Mixed
eremef, Hacker News commenter
Comment on: Beta Player: unofficial Bandcamp desktop and mobile player with remote controlHacker News comment
eremef built an open-source Bandcamp player mostly in Antigravity on Google AI Pro, but quotas ran short and Playwright tests sent the agent into fix-and-test loops.
Published Mar 3, 2026self-described: Solo open-source app, a month of full-time work
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Google AI Pro
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-03-03, Google AI Pro
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Reliability, run stability: repeats a stronger account in its group
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Google AI Pro, all available models
Mixed
measurablefunc, Hacker News commenter
Comment on: I don't know how you get here from "predict the next word"Hacker News comment
Auto-running cargo and test commands burned their daily tokens without progress; switching to manual guidance got further within limits.
Published Feb 26, 2026self-described: Personal Rust compiler and VM project
Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-26
Counts toward
Operational control, execution control: favorable, G2 (2 units before bounds)
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE
Mixed
Domenico Tenace, open-source developer
Adding Capacitor to Glif with Antigravity: The Good, The Bad, and The Reality CheckPersonal blog post, dev.to (Playful Programming)
Antigravity handled Capacitor setup and plugins, but failed to diagnose a Gradle error after three tries, which Domenico Tenace then fixed by hand in five minutes.
Published Feb 26, 2026self-described: Turning a Nuxt app into a mobile app
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-26
Counts toward
Delivered outcomes, task completion: mixed, G2 (2 units before bounds)
Counts toward
Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds)
Counts toward
Adoption and upkeep, setup: mixed, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Negative
Abisheak_Shill, Abisheak Shill, Google AI Pro subscriber
Unacceptable Antigravity Quotas for Gemini 3.1 Pro: Workflow Completely Blocked!Forum post
Mid-way through a large Next.js redesign, their Gemini 3.1 Pro quota sat at 20 percent with a 35-hour reset despite days of no use, while Claude models had room left.
Published Feb 21, 2026self-described: Next.js redesign for a client project
Practitioner account, pseudonymous; direct use; not counted, earlier release How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly; Out of date (Gemini 3.1 Pro (High)); Specific details
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-21, Gemini 3.1 Pro (High), out of date
Not counted
Cost predictability and limits, limits in practice: excluded, describes an earlier release or was retracted
Not counted
Cost predictability and limits, cost predictability: excluded, describes an earlier release or was retracted
Not counted
Cost predictability and limits, cost transparency: excluded, describes an earlier release or was retracted
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward nothing current
Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Out of date
Observed on
Google AI Pro, Gemini 3.1 Pro
Positive
nprateem, Hacker News commenter
Comment on: Ask HN: Are you using an agent orchestrator to write code?Hacker News comment
nprateem runs several distinct tasks across Antigravity agents on a 500k+ line codebase, reviews architecture and reuse closely, and says the setup lets them do the work of three or four people.
Published Feb 13, 2026self-described: Solo on a 500k+ line codebase
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-13
Counts toward
Delivered outcomes, context handling: favorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Negative
mercutio2, Hacker News commenter
Comment on: Zed editor switching graphics lib from blade to wgpuHacker News comment
Calls Antigravity possibly the worst GUI experience since Clippy, filled with arcane buttons and effectively modal prompts in at least 3 places. Despite Google giving away absurdly generous free tokens, can't bring themselves to use it because they get stuck mid-feature.
Published Feb 13, 2026self-described: Personal feature work
Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-13
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Antigravity IDE
Negative
TheAceOfHearts, Hacker News commenter
Comment on: Claude Code is suddenly everywhere inside MicrosoftHacker News comment
TheAceOfHearts found Antigravity undercooked for agentic work: Gemini 3 fixated on unimportant details where Claude found the bugs and the bigger picture.
Published Feb 2, 2026self-described: Personal agentic coding
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on Gemini 3
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-02-02, Gemini 3
Not counted
Delivered outcomes, context handling: repeats a stronger account in its group
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE, Gemini 3
Negative
SMTH_Gaming, SMTH Gaming, Google AI Pro subscriber
Google AI Pro Subscription: Antigravity Quota Not Working as Advertised (10-Day Lockout Instead of 5-Hour Reset)Forum post
During a deep code analysis SMTH_Gaming was locked out for about ten days on Google AI Pro, against the advertised five-hour refresh.
Published Jan 25, 2026self-described: Code analysis of a local repository
Practitioner account, pseudonymous; direct use; counts toward Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Artifact checked (log); Observed on Google AI Pro
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
2 artifacts (log)
Date and version
2026-01-25, Google AI Pro
Counts toward
Cost predictability and limits, cost predictability: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Counts toward
Cost predictability and limits, limits in practice: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Quotas & Plan Changes: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Google AI Pro
Positive
Domenico Tenace, open-source developer
Google Antigravity vs GitHub Copilot: Why I'm Team Antigravity NowPersonal blog post, dev.to (Playful Programming)
After refactoring the Easy Kit Utils library with Antigravity, Domenico Tenace prefers it to Copilot for multi-file work. The agent plans first, waits for approval, then applies changes across dozens of files.
Published Jan 23, 2026self-described: Refactoring their Easy Kit Utils library
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Operational control, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; No tie to Google Antigravity found in GILD's check; Used it directly; Observed on public preview; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, author profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-23, public preview
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, context handling: favorable, G2 (2 units before bounds)
Counts toward
Operational control, execution control: favorable, G2 (2 units before bounds)
Counts toward
Cost predictability and limits, cost transparency: favorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Not counted
Operational control, admin control: repeats a stronger account in its group
Not counted
Operational control, data control: repeats a stronger account in its group
Not counted
Adoption and upkeep, setup: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
defatigable, Hacker News commenter
Comment on: Ask HN: Do you have any evidence that agentic coding works?Hacker News comment
Pointed at their decade-old Chrome extension, Antigravity improved its UI, performance and dependencies in five minutes; defatigable works plan first and approves each step.
Published Jan 21, 2026self-described: Personal Chrome extension; uses Augment at work
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-21
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
Kerrick, Hobbyist Rubyist
Comment on: Ask HN: Do you have any evidence that agentic coding works?Hacker News comment
Mostly with Antigravity, Kerrick shipped a Ruby and Rust TUI library in a month: about 8,600 production code lines plus 11,900 lines of tests, now used by Sidekiq.
Published Jan 21, 2026self-described: Solo open-source library, built in public
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
2 artifacts (repository, issue)
Date and version
2026-01-21
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, correctness: favorable, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
- Overall signal
- Faster on directed work
Published on
Developer Communities
Who
Individual practitioner
Evidence
Measured
Applies to
Still applicable
Negative
Etienne, Google AI Ultra subscriber
Antigravity broken: getting only "Agent execution terminated due to error."Forum post
On Ultra, every prompt ended in "Agent execution terminated due to error" for hours regardless of model, after resets, re-authentication and cache clearing.
Published Jan 15, 2026self-described: Daily development on macOS
Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Specific details; Observed on Google AI Ultra Subscriber
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-15, Google AI Ultra Subscriber
Counts toward
Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Reliability: Raised as a concern
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Google AI Ultra, Antigravity IDE
Positive
Zachary Flower, developer
Vibe Mapping: Google's Antigravity is pretty damn amazingPersonal blog post, flower.codes
Pointed at the source of an old MUD, Antigravity worked out the proprietary area-file format and built a map explorer, about 80 percent on its own in an hour.
Published Jan 15, 2026self-described: Hobby tool for a MUD codebase
Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-15
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds), capped: C-relationship
Not counted
Delivered outcomes, context handling: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
neomantra, Hacker News commenter
Comment on: What happened to WebAssemblyHacker News comment
A verification page neomantra could not finish by hand in hours was one-shotted with Antigravity and Gemini 3, followed by a full in-browser DuckDB data explorer.
Published Jan 9, 2026self-described: Open-source MCP server project
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini 3
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-09, Gemini 3
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Antigravity IDE, Gemini 3
Positive
Linus Torvalds, creator of Linux
AudioNoise READMEProject README, GitHub
Torvalds reports that the Python visualizer in a repo of toy digital guitar effects, made to learn digital audio processing basics, was basically written by vibe-coding with Google Antigravity, since the author knows more about analog filters than Python.
Published Jan 9, 2026self-described: Personal audio effects project
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-09
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship, C-origin
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
mythz, Hacker News commenter
Comment on: How Google got its groove back and edged ahead of OpenAIHacker News comment
After a rough launch, a month of full-time use on the US$20 Pro plan brought no quota hits or failed responses, and Antigravity became their primary coding assistant.
Published Jan 8, 2026self-described: Solo, full-time development
Practitioner account, pseudonymous; direct use; counts toward Reliability, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; Customer of Google Antigravity; Used it directly; Observed on Gemini 3 Pro; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
customer (self disclosed); customer (self disclosed); customer (self disclosed)
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-08, Gemini 3 Pro
Counts toward
Reliability, service availability: mixed, G2 (2 units before bounds)
Counts toward
Cost predictability and limits, limits in practice: favorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, correctness: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Google AI Pro, Gemini 3 Pro
Positive
jchw, Hacker News commenter
Comment on: How Google got its groove back and edged ahead of OpenAIHacker News comment
Running Antigravity for hours on hard debugging problems, jchw saw it break out of loops and make real progress, using gdb in batch mode on crashes.
Published Jan 8, 2026self-described: Personal Rust projects
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes, Reliability How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini 3 Pro
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-08, Gemini 3 Pro
Counts toward
Reliability, run stability: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE, Gemini 3 Pro
Mixed
alwinaugustin, Hacker News commenter
Comment on: Ask HN: Any example of successful vibe-coded product?Hacker News comment
alwinaugustin uses the Antigravity IDE when Claude Code limits run out, which happens often, and still rates Claude best, especially with skills.
Published Jan 4, 2026self-described: Solo, shipping small SaaS apps
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-04
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
contractorwolf, Software engineer
Comment on: Ask HN: Any example of successful vibe-coded product?Hacker News comment
A software engineer built the first version of a carb-estimating web app, serverless on Cloud Run, in about two days with Antigravity.
Published Jan 3, 2026self-described: Solo, consumer app MVP
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2026-01-03
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Positive
Steve Sink, VP of Technology at Just Landed Jets
How Google’s Antigravity IDE Changed My Perspective on Small-Team Software DevelopmentCompany blog post, Just Landed Jets
Had the whole team test Antigravity. Their lead developer, who had resisted AI editors, used it to refactor the VP's working but unmaintainable lead scoring model into a deployable codebase in a few hours. Some best practices it listed fit only their project, and neither of them understood every cleanup decision.
"Our lead developer tested Antigravity on my code. He applied his decade of development experience to guide it. A few hours later, he had a fully refactored version of my project and called me genuinely excited by the quality of the output."
Excerpt, Steve Sink
Published Dec 23, 2025self-described: Private jet charter broker with a small team and one lead developer who deploys internal models
Practitioner account; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Used it directly
Role
Name unknown; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-12-23
Counts toward
Delivered outcomes, task completion: mixed, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Counts toward
Delivered outcomes, correctness: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship, C-unknown-control
Counts toward
Delivered outcomes, context handling: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship, C-unknown-control
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Technical leadership
Evidence
Reported
Applies to
Still applicable
Observed on
Antigravity IDE at launch, used to refactor and compare two repositories
Negative
Piotr Migdał, Quesma
Antigravity feels heavy and Claude Skills are lightCompany blog post, Quesma blog
Building the same Slidev deck in Antigravity and Claude Code, Piotr Migdał found Antigravity slow and under-polished. It ran out of tokens quickly, and he went back to Claude Code.
Published Dec 16, 2025self-described: Side-by-side test against Claude Code
Practitioner account, self-described; structured test; counts toward Delivered outcomes, Cost predictability and limits How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Observed on Gemini 3 Pro; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2025-12-16, Gemini 3 Pro
Counts toward
Delivered outcomes, task completion: mixed, G2 (2 units before bounds), capped: C-relationship
Counts toward
Cost predictability and limits, limits in practice: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Not counted
Reliability, run stability: a lead (G0), counts toward nothing until substantiated
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE, Gemini 3 Pro, Nano Banana Pro
Positive
scotty79, Hacker News commenter
Comment on: AI agents are starting to eat SaaSHacker News comment
scotty79 built a side-by-side HTML diff tool in Antigravity in one evening, correcting the agent repeatedly when it ignored uv and shipped template mistakes.
Published Dec 15, 2025self-described: Solo, one-evening tool build
Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-12-15
Counts toward
Delivered outcomes, task completion: favorable, G2 (2 units before bounds)
Counts toward
Delivered outcomes, correctness: mixed, G2 (2 units before bounds)
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Negative
Manish, independent security researcher
AI IDE prompt Injection: Reading browser local storageSecurity research blog post, introvertmac.wordpress.com
Manish shows a repository whose README or GEMINI.md tells the agent to open an HTML file without confirmation, letting the page read cookies and local storage.
Published Dec 15, 2025self-described: Personal security testing
Practitioner account; direct use; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Used it directly; Specific details
Role
Name unknown; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
1 artifact (vendor reply)
Date and version
2025-12-15
Counts toward
Operational control, execution control: unfavorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Permissions & Safety: Raised as a concern
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Positive
Philipp Hartenfeller, Product Lead at United Codes
This blog is now on Astro thanks to Antigravity!Personal blog post, hartenfeller.dev
Antigravity with Gemini 3 Pro migrated their blog's React components from Gatsby to Astro over several bug-fixing iterations without being prompted to continue.
Published Dec 8, 2025self-described: Personal blog migration
Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly; Observed on Gemini 3 Pro
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-12-08, Gemini 3 Pro
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Delivered outcomes, correctness: favorable, G1 (1 unit before bounds), capped: C-relationship
Counts toward
Reliability, run stability: favorable, G1 (1 unit before bounds), capped: C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Antigravity IDE, Gemini 3 Pro
Negative
Aaryan Bhujang, AI security researcher at Repello AI
Google Antigravity Security: The Zero-Click Exfiltration Google Won’t FixSecurity research write-up, Repello AI blog
Repello built a test repository whose files carry fake system messages, and Antigravity's agent followed them, encoding API keys and environment variables and sending them to an outside webhook after a single integration request. Google classified the report as expected behavior.
"A single integration request triggers automatic credential exfiltration without additional user interaction…"
Excerpt, Aaryan Bhujang
"The AI cannot distinguish between legitimate ephemeral messages from the system and malicious ones…"
Same speaker
Published Nov 28, 2025AI security company red teaming coding agents
Practitioner account, name and role on their organization's own page; structured test; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Name and role on their organization's own page; Ran a structured test; Artifact checked (log)
Role
Name on a page the person does not control; employer on a page the person does not control; role on a page the person does not control (AI Security Researcher, Repello AI)
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
1 artifact (log)
Date and version
2025-11-28
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Permissions & Safety: Raised as a concern
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity agent opening a malicious repository, with Turbo mode
Mixed
Amit Gawande, developer
Antigravity's Gemini ProblemPersonal blog post, Amit Gawande's Devlog
Amit Gawande likes the agent-first interface, artifacts and browser subagents, but found Gemini 3 Pro's code and the limited quota the obstacles to beating Claude Code.
Published Nov 26, 2025self-described: Standard agentic-IDE test against Claude Code
Practitioner account, self-described; structured test; counts toward Delivered outcomes, Operational control, Cost predictability and limits, Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Observed on Gemini 3 Pro; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
1 artifact (transcript)
Date and version
2025-11-26, Gemini 3 Pro
Counts toward
Adoption and upkeep, setup: favorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Delivered outcomes, correctness: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Counts toward
Cost predictability and limits, limits in practice: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Counts toward
Operational control, execution control: unfavorable, G1 (1 unit before bounds), capped: C-relationship
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE, Gemini 3 Pro
Negative
PromptArmor, AI security research team
Google Antigravity Exfiltrates DataSecurity research write-up, PromptArmor
The team showed a poisoned integration guide steering Gemini in Antigravity to read .env credentials despite a gitignore setting and send them out through the browser subagent.
Published Nov 25, 2025self-described: Security team testing Antigravity against prompt injection
Practitioner account, self-described; structured test; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
No artifact or independent corroboration recorded
Date and version
2025-11-20
Counts toward
Operational control, execution control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Counts toward
Operational control, data control: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Reported
Applies to
Needs a recheck
Negative
Aaron Portnoy, Chief Product Officer at Mindgard
Forced Descent: Google Antigravity Persistent Code Execution VulnerabilitySecurity research write-up, Mindgard blog
Portnoy of Mindgard shows a malicious trusted workspace can plant a global MCP config that runs code on every Antigravity launch, even after uninstall and reinstall and in the most restrictive mode. Google closed the report as Won't Fix (Intended Behavior), then re-opened it.
"At the moment, there is no setting that we’re aware of that can be used to protect against this vulnerability."
Excerpt, Aaron Portnoy
Published Nov 25, 2025AI security company testing Antigravity's workspace trust model
Practitioner account, self-described; structured test; counts toward Operational control How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Ran a structured test; Artifact checked (transcript); Observed on Gemini 3 Pro
Role
Name self-described; employer self-described; role self-described (Aaron Portnoy is Mindgard's Chief Product Officer)
Relationship
Checked only from the record itself; an outside check is open
How they know
Ran a structured test
Support
1 artifact (transcript)
Date and version
2025-11-25, Gemini 3 Pro
Counts toward
Operational control, execution control: unfavorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Overall signal
- Permissions & Safety: Raised as a concern
Published on
Engineering Blogs & Reviews
Who
Professional team
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE with terminal execution set to Off and review-driven settings
Mixed
elevatortrim, Hacker News commenter
Comment on: Nano Banana ProHacker News comment
elevatortrim's company wants to move from Claude to Gemini and calls Antigravity a possible Claude Code replacement, but without a capped monthly subscription for a company account the pricing blocks the switch.
Published Nov 21, 2025self-described: Company weighing a move from Claude to Gemini for agentic coding and employee use
Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Opinion
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2025-11-21
Not counted
no aspect: excluded, takes no position on any assessed aspect
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Quotas & Plan Changes: Raised as a concern
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Needs a recheck
Positive
Christopher Krapu, data scientist
Using Antigravity for Statistical Physics in JavaScriptPersonal blog post, christopherkrapu.com
In an hour, Antigravity with Gemini 3 Pro built a JavaScript visualization of the Ising model. The author says the Chrome browser extension for retrieving the DOM really helped too, and calls UI features like showing subtasks a little unnecessary.
Published Nov 21, 2025self-described: Personal visualization test
Practitioner account, self-described; direct use; counts toward Delivered outcomes How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly; Specific details; Observed on Gemini 3 Pro
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-21, Gemini 3 Pro
Counts toward
Delivered outcomes, task completion: favorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Antigravity IDE, Gemini 3 Pro
Negative
sega_sai, Hacker News commenter, Gemini Pro subscriber
Comment on: Google AntigravityHacker News comment
About ten minutes into their first session sega_sai hit a model quota limit with no reset time shown, and judged Google's coding tools less finished than Claude Code.
Published Nov 19, 2025self-described: Personal trial
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details; Observed on Gemini Pro
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-19, Gemini Pro
Not counted
Cost predictability and limits, limits in practice: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE at launch
Negative
timtimmy, Hacker News commenter
Comment on: Building more with GPT-5.1-Codex-MaxHacker News comment
Before trying Antigravity on their team's codebase timtimmy read the terms, found Google trains on prompts and source code with no paid opt-out at launch, and held back.
Published Nov 19, 2025self-described: Evaluating Antigravity for a team codebase
not counted, repeats a stronger account How GILD checked it
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Opinion, no use stated
Support
No artifact or independent corroboration recorded
Date and version
2025-11-19
Not counted
Operational control, data control: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
- Data Privacy: Raised as a concern
Published on
Developer Communities
Who
Very small team
Evidence
Reported
Applies to
Needs a recheck
Positive
Yeroc, Hacker News commenter
Comment on: Google AntigravityHacker News comment
Within about 20 minutes Yeroc found the two features they had been looking for: the Agent Manager view of all agents across workspaces, and inline code comments routed to the active agent.
Published Nov 18, 2025self-described: Personal trial; only Claude Code is approved at work
Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-18
Not counted
Operational control, execution control: repeats a stronger account in its group
Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Antigravity IDE at launch
Negative
Topfi, Hacker News commenter
Comment on: Google AntigravityHacker News comment
After two hours Topfi found it buggy, unreliable with terminal commands and tool calls, and willing to call a task done despite issues visible in its own browser screenshot.
Published Nov 18, 2025self-described: Personal trial on launch day
Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
Origin
Published practitioner account
Checked
Pseudonymous; No tie to Google Antigravity found in GILD's check; Used it directly; Specific details
Role
Pseudonymous account; identity not pursued
Relationship
No tie to Google Antigravity found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-18
Counts toward
Adoption and upkeep, setup: unfavorable, G2 (2 units before bounds)
Not counted
Delivered outcomes, task completion: repeats a stronger account in its group
Not counted
Reliability, run stability: repeats a stronger account in its group
Not counted
Operational control, data control: repeats a stronger account in its group
Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard
Counts toward, pending a recheck
Published on
Developer Communities
Who
Individual practitioner
Evidence
Reported
Applies to
Needs a recheck
Observed on
Antigravity IDE at launch, Gemini 3 Pro
Mixed
Simon Willison, independent developer and blogger
Google AntigravityPersonal blog post, simonwillison.net
Simon Willison found Antigravity more interesting than a Cursor clone, with an agent manager, browser testing and artifacts, but their first task ended in a model provider overload error.
Published Nov 18, 2025self-described: Personal open-source plugin work
Practitioner account, self-described; direct use; counts toward Reliability How GILD checked it
Origin
Published practitioner account
Checked
Self-described; Used it directly; Specific details
Role
Name self-described; employer unknown; role unknown
Relationship
Checked only from the record itself; an outside check is open
How they know
Used it directly
Support
No artifact or independent corroboration recorded
Date and version
2025-11-18
Counts toward
Reliability, service availability: unfavorable, G2 (2 units before bounds), capped: C-relationship
Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard
Counts toward
Published on
Engineering Blogs & Reviews
Who
Individual practitioner
Evidence
Reported
Applies to
Still applicable
Observed on
Antigravity IDE at launch

Product documentation 17

Pages from Google, used to check facts for every group.

Plans
States that every plan gets Gemini models, unlimited Tab completions, and the CLI. Google AI Ultra gets the highest quota refreshed every five hours, Pro a high quota refreshed every five hours up to a weekly limit, and other accounts a weekly quota.
Checked Oct 12, 2026
Models
Lists Gemini 3.8 Flash, 3.7 Flash, 3.6 Flash, and 3.1 Pro on every plan, and Claude Sonnet 5.5 and Opus 5.5 on non-trial Pro, Ultra, and Enterprise. Three older models were removed on November 2, 2026.
Checked Oct 12, 2026
Antigravity in Gemini Enterprise
Documents sign-in through Google Cloud SSO, Workforce Identity Federation, or Application Default Credentials, regional endpoints, network allowlists, and that the standalone Antigravity IDE is not supported for enterprise deployments.
Checked Oct 12, 2026
Agent permissions
Defines Deny, Ask, and Allow rules evaluated in that order, and the Default, Request Review, and Turbo presets for terminal, file, MCP, and web actions.
Checked Oct 12, 2026
Terminal sandbox
Describes OS-level isolation of shell commands under the Default preset, with workspace-only file access and no network access unless the user approves.
Checked Oct 12, 2026
Managing AI credits and quotas (CLI)
Documents the statusline credit count, the /credits panel, and the setting that lets the CLI spend personal AI credits when plan quota runs out.
Checked Oct 12, 2026
IDE extensions
Lists the VS Code, Visual Studio, JetBrains, Zed, and Xcode extensions and states that, under Gemini Enterprise, code, prompts, and agent transcripts are not used to train Google foundation models.
Checked Oct 12, 2026
Migrating from Gemini CLI
Documents importing Gemini CLI extensions as Antigravity plugins, moving skills paths, and reformatting MCP configuration.
Checked Oct 12, 2026
FAQ
Lists supported countries, the 18-and-over requirement, the data-collection opt-out in Settings, and that using third-party software with an Antigravity login violates the terms.
Checked Oct 12, 2026
Changelog
Records Antigravity 2.0 releases through v2.22.0 on October 8, 2026, Antigravity CLI through v1.3.1 on October 7, 2026, and Antigravity IDE through v2.5.5 on August 13, 2026.
Checked Oct 12, 2026
Google Antigravity Additional Terms of Service
States that Google records Interactions, uses them to improve its products and machine learning, may have employees review them, and lets users change that preference in settings. The terms do not apply to Gemini Enterprise access.
Checked Oct 12, 2026
Changes to Antigravity plans
Announces on May 19, 2026 a US$100 Google AI Ultra tier and cuts the top Ultra tier from US$250 to US$200 a month. Gemini models now share one quota, and AI credits cover overage only.
Checked Oct 12, 2026
Bringing Antigravity to Gemini Enterprise
Reports that eligible Gemini Enterprise Standard and Plus subscriptions include Antigravity from August 20, 2026, with IDE extensions, budget caps, and audit logging.
Checked Oct 12, 2026
AI developer tools overview
Lists Antigravity 2.0, the Antigravity CLI, and Antigravity for IDEs on Gemini Enterprise Standard, Plus, and Pay-as-you-go, and the certifications it does not yet support, including SOC 2 and ISO 27001.
Checked Oct 12, 2026
Configure AI developer tools settings
Documents administrator controls for file access outside the workspace, terminal auto-execution, sandboxing, browser and MCP access, audit logging, and authorized models, with their defaults.
Checked Oct 12, 2026
Quotas and pay-as-you-go usage
States that Standard includes US$10 and Plus US$15 of Antigravity credit per user per month, pooled across licensed users and enforced over rolling seven days.
Checked Oct 12, 2026
Gemini Code Assist Standard and Enterprise subscriptions
Confirms that new Code Assist Standard and Enterprise subscriptions cannot be bought from October 9, 2026 and that agentic coding moves to Antigravity in Gemini Enterprise.
Checked Oct 12, 2026

Source index

Provenance at a glance

Every source GILD read, with the original address and the context used to count it. Open a finding to filter the full cards above. On smaller screens the index lists each source once by name, cohort and date; its full record above carries the address, context and findings.

Provenance for every analyzed Signals source
Source	Original URL	Author and context	Who	Published	Review date	Applies	Findings
Antigravity agent stuck in endless file-reading loop (Gemini models)ID dc-90 \| Developer Communities	discuss.ai.google.dev/t/antigravity-agent-stuck-in-endless-file-reading-loop-gemini-models/188526	SuneraX, Antigravity userself-described: App development	Individual practitioner	Published Oct 12, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Model Access: Positive Reliability: Raised as a concern
Antigravity CLI: Workspace and Google AI Pro accounts are practically unusableID dc-91 \| Developer Communities	discuss.ai.google.dev/t/antigravity-cli-workspace-and-google-ai-pro-accounts-are-practically-unusable/188232	Hans, runs a team's AI agents on its own serverself-described: Daily operations with several AI agents on a company server	Very small team	Published Oct 12, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Quotas & Plan Changes: Raised as a concern Product Direction: Raised as a concern
Comment on: I made an open-source Boom 3D clone. Wanna check it out?ID dc-92 \| Developer Communities	news.ycombinator.com/item?id=50049546	joaoviniciusgs, Hacker News commenterself-described: Solo open-source Rust and Tauri app	Individual practitioner	Published Oct 12, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Multi-Step Execution: Positive Written rules improve results
Comment on: OpenSCAD the Programmers Solid 3D CAD ModellerID dc-89 \| Developer Communities	news.ycombinator.com/item?id=50037556	georgemcbay, Long-time OpenSCAD userself-described: Hobby CAD	Individual practitioner	Published Oct 10, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Works best on bounded tasks How does Antigravity compare with the other coding agents engineers use?: Competitive
Comment on: Gemini 4 ArgonID dc-87 \| Developer Communities	news.ycombinator.com/item?id=49916498	tinyhouse, Hacker News commenter, former Pro subscriberself-described: Compared more than five harnesses	Individual practitioner	Published Oct 1, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Gemini 4 ArgonID dc-88 \| Developer Communities	news.ycombinator.com/item?id=49916546	mapontosevenths, Hacker News commenter, Google AI Ultra subscriberself-described: Terminal workflows	Individual practitioner	Published Oct 1, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Mixed or negative Reliability: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Gemini 4 ArgonID dc-82 \| Developer Communities	news.ycombinator.com/item?id=49913755	taylorfinley, Hacker News commenterself-described: Personal local-model setup	Individual practitioner	Published Sep 30, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Multi-Step Execution: Positive
Comment on: Gemini 4 ArgonID dc-83 \| Developer Communities	news.ycombinator.com/item?id=49914707	smartbit, Hacker News commenterself-described: Documentation and coding in the terminal	Individual practitioner	Published Sep 30, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Mixed or negative Permissions & Safety: Raised as a concern
Comment on: Gemini 4 ArgonID dc-84 \| Developer Communities	news.ycombinator.com/item?id=49915315	huydotnet, Hacker News commenterself-described: Personal; Google AI Pro through their phone carrier	Individual practitioner	Published Sep 30, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Model Access: Positive Quotas & Plan Changes: Discussed without concern Works best on bounded tasks
Comment on: Gemini 4 ArgonID dc-85 \| Developer Communities	news.ycombinator.com/item?id=49915373	martythemaniak, Hacker News commenterself-described: Robotics hobby project	Individual practitioner	Published Sep 30, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Multi-Step Execution: Positive Quotas & Plan Changes: Discussed without concern
Comment on: Gemini 4 ArgonID dc-86 \| Developer Communities	news.ycombinator.com/item?id=49915434	piyh, Hacker News commenterself-described: Parallel work in worktrees	Individual practitioner	Published Sep 30, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Mixed or negative Quotas & Plan Changes: Discussed without concern Product Direction: Raised as a concern
Stress Test: 100% Antigravity + Gemini Flash, 102.8B tokens and 474K LOCID ir-23 \| Engineering Blogs & Reviews	github.com/Janson79jc/antigravity-100b-telemetry-audit	Janson79jc, solo developerself-described: Solo, 474K line codebase over 465 sessions	Individual practitioner	Published Sep 27, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Reliability: Raised as a concern Faster on directed work
Comment on: Plan mode is deadID dc-81 \| Developer Communities	news.ycombinator.com/item?id=49855463	parasti, Hacker News commenterself-described: Hobby projects; Claude Code at work	Individual practitioner	Published Sep 26, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Plans & Artifacts: Positive How much work should Antigravity complete before a human checkpoint?: Tighter steering
Severe slowdowns and frequent 503 errors on Gemini Flash 3.8 during specific hoursID dc-80 \| Developer Communities	discuss.ai.google.dev/t/issue-report-severe-slowdowns-and-frequent-503-errors-on-gemini-flash-3-8-during-specific-hours-are-server-resources-being-intentionally-throttled/184984	Freya Smith, uses Antigravity for workself-described: Daily work between 16:00 and 22:00 UTC	Individual practitioner	Published Sep 25, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Reliability: Raised as a concern
Problem with antigravity CLI using shell commands for everythingID dc-79 \| Developer Communities	discuss.ai.google.dev/t/problem-with-antigravity-cli-using-shell-commands-for-everything/184449	flying_manta, Antigravity CLI userself-described: Daily CLI use	Individual practitioner	Published Sep 23, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Reliability: Raised as a concern
We All Have a "Serious Work" AI and a "Just Vibing" AI. When Did That Happen?ID ir-22 \| Engineering Blogs & Reviews	dev.to/dj29/we-all-have-a-serious-work-ai-and-a-just-vibing-ai-when-did-that-happen-5fl2	Dhruv Jani, developerself-described: Daily IDE work	Individual practitioner	Published Sep 22, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Model Access: Positive Browser Verification: Mixed or negative Is Antigravity the team's main coding tool, or one beside another?: Main tool
Comment on: GPT-5.6 Luna vs. GPT-6 Astra: Is a US$1.20 Model Good Enough for Code Review?ID dc-78 \| Developer Communities	news.ycombinator.com/item?id=49703968	dlahoda, Engineer running a review orchestration on their team's repositoryself-described: Team repository with several review bots	Very small team	Published Sep 14, 2026	Assessment reviewed Nov 1, 2026	Current	Is Antigravity the team's main coding tool, or one beside another?: Second tool
Comment on: Ask HN: What default model do you use and why?ID dc-76 \| Developer Communities	news.ycombinator.com/item?id=49673239	vallerie, Hacker News commenterself-described: Plan and test-harness driven work	Individual practitioner	Published Sep 12, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive Works best on bounded tasks
Comment on: Benchmark: CadQuery vs. OpenSCAD for agentic CAD workID dc-77 \| Developer Communities	news.ycombinator.com/item?id=49677624	evilduck, Hacker News commenterself-described: Home and hobbyist CAD for 3D printing	Individual practitioner	Published Sep 12, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Multi-Step Execution: Positive
Comment on: GPT-6 AstraID dc-75 \| Developer Communities	news.ycombinator.com/item?id=49580086	rafaelmn, Hacker News commenterself-described: Long-planned side project	Individual practitioner	Published Sep 5, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Requires Strong Review: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Gemini 3.8 Flash and 3.8 Flash CyberID dc-74 \| Developer Communities	news.ycombinator.com/item?id=49545995	allthetime, Hacker News commenterself-described: Company codebase: web, React Native, CMS, ETL and websocket services	Very small team	Published Sep 3, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Multi-Step Execution: Positive Plans & Artifacts: Positive Needs Close Steering: Discussed without concern Is Antigravity the team's main coding tool, or one beside another?: Main tool
Antigravity's terms of service and third-party useID sx-01 \| Developer Communities	x.com/GergelyOrosz/status/2095453567955968398	Gergely Orosz, author of The Pragmatic Engineerself-described: Writes about engineering teams and their tooling; deciding whether to use Antigravity himself	Individual practitioner	Published Sep 3, 2026	Assessment reviewed Nov 1, 2026	Current	Data Privacy: Raised as a concern
Comment on: Google Antigravity introduces Boost deep reasoning (/boost)ID dc-70 \| Developer Communities	news.ycombinator.com/item?id=49518186	dpweb, Hacker News commenter, student planself-described: Personal devops and home network	Individual practitioner	Published Sep 1, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Multi-Step Execution: Positive Quotas & Plan Changes: Discussed without concern
Comment on: Google Antigravity introduces Boost deep reasoning (/boost)ID dc-71 \| Developer Communities	news.ycombinator.com/item?id=49518376	sanarothe, Non-software engineerself-described: Personal projects on a personal plan	Individual practitioner	Published Sep 1, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Plans & Artifacts: Positive Parallel Agents: Positive Quotas & Plan Changes: Discussed without concern
Comment on: Google Antigravity introduces Boost deep reasoning (/boost)ID dc-72 \| Developer Communities	news.ycombinator.com/item?id=49518393	dan_voronov, Blogger reviewing AI programming toolsself-described: Long-term testing of Antigravity 1 and 2	Individual practitioner	Published Sep 1, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Mixed or negative Value for Money: Positive Quotas & Plan Changes: Discussed without concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Google Antigravity introduces Boost deep reasoning (/boost)ID dc-73 \| Developer Communities	news.ycombinator.com/item?id=49520077	leoedin, Hacker News commenter, former subscriberself-described: Personal use	Individual practitioner	Published Sep 1, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Quotas & Plan Changes: Raised as a concern
Comment on: Our decision on Cursor following its acquisition by SpaceXID dc-69 \| Developer Communities	news.ycombinator.com/item?id=49487793	hn_throw2025, Hacker News commenter, former Cursor subscriberself-described: Uses Antigravity 2.0 beside a JetBrains IDE	Individual practitioner	Published Aug 29, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Plans & Artifacts: Positive Product Direction: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Competitive
Comment on: Why does Opus 5 feel worse to work with?ID dc-68 \| Developer Communities	news.ycombinator.com/item?id=49298209	slaser79, Hacker News commenterself-described: Holds Anthropic, OpenAI and Google subscriptions	Individual practitioner	Published Aug 14, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive Works best on bounded tasks Is Antigravity the team's main coding tool, or one beside another?: Second tool
Nothing to See Here: How an AI Agent Buried Its Own CommandsID ld-06 \| Engineering Blogs & Reviews	www.straiker.ai/blog/google-antigravity-ai-agent-prompt-injection	Jesus Padilla Soqui, Straiker STAR teamself-described: Agentic AI security company assessing the Antigravity platform	Professional team	Published Aug 14, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Permissions & Safety: Raised as a concern
Preventing Quota Crashes via Antigravity CLI Agent HooksID ir-21 \| Engineering Blogs & Reviews	dev.to/gde/preventing-quota-crashes-via-antigravity-cli-agent-hooks-24hd	Tanaike, Google Developer Expertself-described: Autonomous Antigravity CLI sessions	Individual practitioner	Published Aug 12, 2026	Assessment reviewed Nov 1, 2026	Current	Not counted. Its author is a Google Developer Expert, a program Google runs.
Comment on: Discovery LoopID dc-67 \| Developer Communities	news.ycombinator.com/item?id=49187200	qlte, Hacker News commenter, Google AI Pro subscriberself-described: Personal use after the Gemini CLI shutdown	Individual practitioner	Published Aug 5, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Quotas & Plan Changes: Raised as a concern
Comment on: So what is your programming setup? Hype is making fundamentals confusingID dc-66 \| Developer Communities	news.ycombinator.com/item?id=49069669	malkamius, Hacker News commenterself-described: Hobby game add-ons, run in a VM	Individual practitioner	Published Jul 27, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Permissions & Safety: Discussed without concern How much work should Antigravity complete before a human checkpoint?: Broader delegation
Comment on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash CyberID dc-64 \| Developer Communities	news.ycombinator.com/item?id=49000337	dudeinhawaii, Hacker News commenter, former Google AI Ultra subscriberself-described: Daily use of several providers	Individual practitioner	Published Jul 22, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Reliability: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash CyberID dc-65 \| Developer Communities	news.ycombinator.com/item?id=49000731	tobias2014, Hacker News commenterself-described: Complex problems, run semi-autonomously	Individual practitioner	Published Jul 22, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Reliability: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash CyberID dc-62 \| Developer Communities	news.ycombinator.com/item?id=48994254	stonewhite, Hacker News commenter buying AI tools for their companyself-described: Company that standardized on Google AI Ultra	Very small team	Published Jul 21, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern Product Direction: Raised as a concern
Comment on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash CyberID dc-63 \| Developer Communities	news.ycombinator.com/item?id=48994491	mythz, Hacker News commenterself-described: Solo, full-time development	Individual practitioner	Published Jul 21, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Model Access: Positive Is Antigravity the team's main coding tool, or one beside another?: Main tool
Comment on: Kimi K3, Qwen 3.8, and Anthropic's (Potential) UnravellingID dc-61 \| Developer Communities	news.ycombinator.com/item?id=48980761	mwryl, Hacker News commenterself-described: Team building products on low-cost models; replaced Antigravity for development	Very small team	Published Jul 20, 2026	Assessment reviewed Nov 1, 2026	Current	How does Antigravity compare with the other coding agents engineers use?: Behind
Trusted automation with Google Antigravity: Scaling secure finance integrations from 40 Days to 5ID ir-20 \| Engineering Blogs & Reviews	discuss.google.dev/t/trusted-automation-with-google-antigravity-scaling-secure-finance-integrations-from-40-days-to-5/383313	Rohan Soni, Google, writing Inspired Entertainment's case study with its CTOself-described: Integration team building Java Spring Boot wallet adapters	Professional team	Published Jul 20, 2026	Assessment reviewed Nov 1, 2026	Current	Not counted. Google wrote and published this case study.
The Week of Sandbox Escapes Day 1: Escaping Antigravity's Allow-Default SeatbeltID ld-04 \| Engineering Blogs & Reviews	www.pillar.security/blog/escaping-antigravitys-allow-default-seatbelt	Dan Lisichkin, security researcher at Pillar SecurityPillar Research team testing agentic IDE sandboxes on macOS	Professional team	Published Jul 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Permissions & Safety: Raised as a concern
Starting and iterating on a Kaggle competition in Google AntigravityID ir-19 \| Engineering Blogs & Reviews	andlukyane.com/blog/kaggle-antigravity-s6e7	Andrey Lukyanenko, ML engineer and Google Developer Expertself-described: Kaggle Playground competition	Individual practitioner	Published Jul 9, 2026	Assessment reviewed Nov 1, 2026	Current	Not counted. Its author is a Google Developer Expert, a program Google runs.
Comment on: The classifiers Anthropic puts in front of Fable are too zealousID dc-60 \| Developer Communities	news.ycombinator.com/item?id=48838080	SwellJoe, Developer building a security auditing harnessself-described: Security auditing harness and benchmarks	Individual practitioner	Published Jul 8, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Reliability: Raised as a concern
Ghostfabric: How An AI Coding Agent Was Tricked Into Exfiltrating Data Over VXLANID ld-05 \| Engineering Blogs & Reviews	www.straiker.ai/blog/ghostfabric-how-an-ai-coding-agent-was-tricked-into-exfiltrating-data-over-vxlan	Christopher Tuz, AI security researcher on the STAR Labs team at StraikerAgentic AI security company red teaming coding agents	Professional team	Published Jul 8, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Permissions & Safety: Raised as a concern How much work should Antigravity complete before a human checkpoint?: Tighter steering
Comment on: I'm opening VSCode less and less every dayID dc-59 \| Developer Communities	news.ycombinator.com/item?id=48779053	yogendra6698, Builds AI agents professionallyself-described: Daily development	Individual practitioner	Published Jul 3, 2026	Assessment reviewed Nov 1, 2026	Current	Not counted. Its author is an AI engineer at Google Cloud, and Google makes Antigravity.
Comment on: Google limits Meta's use of its Gemini AI modelsID dc-58 \| Developer Communities	news.ycombinator.com/item?id=48708517	moshegramovsky, Hacker News commenterself-described: Personal C++ development	Individual practitioner	Published Jun 28, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Plans & Artifacts: Positive Reliability: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind Is Antigravity the team's main coding tool, or one beside another?: Second tool
Comment on: Computer use in Gemini 3.5 FlashID dc-57 \| Developer Communities	news.ycombinator.com/item?id=48667192	anigbrowl, Hacker News commenterself-described: New paying Gemini API customer	Individual practitioner	Published Jun 25, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Quotas & Plan Changes: Raised as a concern Product Direction: Raised as a concern
Comment on: AI's Affordability CrisisID dc-56 \| Developer Communities	news.ycombinator.com/item?id=48648590	trollbridge, Hacker News commenter running a small development shopself-described: Small shop that competes with offshore development firms	Very small team	Published Jun 23, 2026	Assessment reviewed Nov 1, 2026	Current	Is Antigravity the team's main coding tool, or one beside another?: Second tool
Comment on: The text in Claude Code's "Extended Thinking" outputID dc-55 \| Developer Communities	news.ycombinator.com/item?id=48632316	linsomniac, Hacker News commenterself-described: Spec-first workflow across agents	Individual practitioner	Published Jun 22, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Requires Strong Review: Discussed without concern Is Antigravity the team's main coding tool, or one beside another?: Second tool
Comment on: John Jumper to join AnthropicID dc-54 \| Developer Communities	news.ycombinator.com/item?id=48607624	bjackman, Hacker News commenterself-described: Personal use of Gemini and Claude	Individual practitioner	Published Jun 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive Requires Strong Review: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Running local models is good nowID dc-53 \| Developer Communities	news.ycombinator.com/item?id=48561663	polotics, Hacker News commenterself-described: Solo Android app, about 10,000 lines of Kotlin	Individual practitioner	Published Jun 16, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Quotas & Plan Changes: Raised as a concern Reliability: Raised as a concern Needs Close Steering: Raised as a concern Written rules improve results
Comment on: DiffusionGemma: 4x Faster Text GenerationID dc-52 \| Developer Communities	news.ycombinator.com/item?id=48481794	evilturnip, Hacker News commenterself-described: Personal projects	Individual practitioner	Published Jun 10, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive Works best on bounded tasks
Comment on: Microsoft starts canceling Claude Code licensesID dc-51 \| Developer Communities	news.ycombinator.com/item?id=48248245	seabrookmx, Hacker News commenterself-described: Team at a large Google Cloud customer	Very small team	Published May 23, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Product Direction: Raised as a concern
Comment on: Google's Antigravity bait and switchID dc-48 \| Developer Communities	news.ycombinator.com/item?id=48230573	mark_l_watson, Retired developer and authorself-described: One-month Google AI Ultra test	Individual practitioner	Published May 22, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Model Access: Positive Product Direction: Raised as a concern Faster on directed work
Comment on: Google's Antigravity bait and switchID dc-49 \| Developer Communities	news.ycombinator.com/item?id=48232794	heyyeah, Hacker News commenterself-described: Installing Antigravity IDE after 2.0	Individual practitioner	Published May 22, 2026	Assessment reviewed Nov 1, 2026	Current	Data Privacy: Raised as a concern
Comment on: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM BenchmarkID dc-50 \| Developer Communities	news.ycombinator.com/item?id=48235971	u8, Developer of CLI developer toolingself-described: Personal site build	Individual practitioner	Published May 22, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Mixed or negative Quotas & Plan Changes: Raised as a concern
Comment on: Google's Antigravity Bait and SwitchID dc-46 \| Developer Communities	news.ycombinator.com/item?id=48223707	daft_pink, Hacker News commenterself-described: Workspace user	Individual practitioner	Published May 21, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Product Direction: Raised as a concern Data Privacy: Raised as a concern
Comment on: Google's Antigravity Bait and SwitchID dc-47 \| Developer Communities	news.ycombinator.com/item?id=48225234	spankalee, Hacker News commenterself-described: Existing Antigravity user	Individual practitioner	Published May 21, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Product Direction: Raised as a concern
My AI Agent Hit Google's Quota Wall in 8 Minutes. 36 Hours Later, Google Tripled the Limits.ID ir-15 \| Engineering Blogs & Reviews	dev.to/ai_made_tools/my-ai-agent-hit-googles-quota-wall-in-8-minutes-36-hours-later-google-tripled-the-limits-mkc	Joske Vermeulen, runs an autonomous agent startup raceself-described: Autonomous agent on cron, US$20 Pro plan	Individual practitioner	Published May 21, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Multi-Step Execution: Positive Quotas & Plan Changes: Raised as a concern How much work should Antigravity complete before a human checkpoint?: Broader delegation
Antigravity CLI First Impressions: Fast, Rough, and Not ReadyID ir-16 \| Engineering Blogs & Reviews	dev.to/jagostoni/antigravity-cli-first-impressions-fast-rough-and-not-ready-522j	Jason Agostoni, developer and author of the Ship Bench benchmarkself-described: Ship Bench run on Windows	Individual practitioner	Published May 21, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Quotas & Plan Changes: Raised as a concern Reliability: Raised as a concern Permissions & Safety: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
OpenSCAD LLM Benchmark: Building the PantheonID ir-17 \| Engineering Blogs & Reviews	modelrift.com/blog/openscad-llm-benchmark/	ModelRift engineering teamself-described: Company benchmarking coding agents for its OpenSCAD product	Professional team	Published May 21, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Multi-Step Execution: Positive Plans & Artifacts: Positive How does Antigravity compare with the other coding agents engineers use?: Competitive
Google's Antigravity Bait and SwitchID ir-18 \| Engineering Blogs & Reviews	www.0xsid.com/blog/antigravity-bait-n-switch	Sid, independent developer on Google AI Ultraself-described: Daily production work	Individual practitioner	Published May 21, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Plans & Artifacts: Positive Reliability: Raised as a concern Product Direction: Raised as a concern Is Antigravity the team's main coding tool, or one beside another?: Main tool
Recent Antigravity Changes Have Seriously Hurt the ExperienceID dc-40 \| Developer Communities	discuss.ai.google.dev/t/recent-antigravity-changes-have-seriously-hurt-the-experience/146237	Madhur Mishra, Antigravity userself-described: Daily development	Individual practitioner	Published May 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Mixed or negative Quotas & Plan Changes: Raised as a concern Product Direction: Raised as a concern
Comment on: Gemini CLI will stop working from June 18, 2026ID dc-41 \| Developer Communities	news.ycombinator.com/item?id=48203205	MisterPea, Hacker News commenterself-described: Personal use across Google tools	Individual practitioner	Published May 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Developer Experience: Positive Quotas & Plan Changes: Raised as a concern
Comment on: Gemini CLI will stop working from June 18, 2026ID dc-42 \| Developer Communities	news.ycombinator.com/item?id=48203609	No1, Hacker News commenterself-described: First trial	Individual practitioner	Published May 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Quotas & Plan Changes: Raised as a concern Reliability: Raised as a concern Permissions & Safety: Raised as a concern
Comment on: Gemini CLI will stop working from June 18, 2026ID dc-43 \| Developer Communities	news.ycombinator.com/item?id=48206621	tegeek, Hacker News commenterself-described: Four months of daily use with Kiro and Claude Code	Individual practitioner	Published May 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Product Direction: Raised as a concern
Comment on: Qwen3.7-Max: The Agent FrontierID dc-44 \| Developer Communities	news.ycombinator.com/item?id=48210341	cft, Hacker News commenter, Google AI Pro subscriberself-described: Personal; Flash for auxiliary tasks	Individual practitioner	Published May 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Value for Money: Mixed or negative Quotas & Plan Changes: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Gemini CLI will stop working from June 18, 2026ID dc-45 \| Developer Communities	news.ycombinator.com/item?id=48213398	almog, Hacker News commenter, Google AI Pro subscriberself-described: Personal firmware reverse engineering	Individual practitioner	Published May 20, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Quotas & Plan Changes: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
I'm done with AntigravityID dc-37 \| Developer Communities	discuss.ai.google.dev/t/im-done-with-antigravity/145455	Vicente Cortes, Google One Pro subscriber for over a yearself-described: Personal projects	Individual practitioner	Published May 19, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Model Access: Positive Quotas & Plan Changes: Raised as a concern Reliability: Raised as a concern Product Direction: Raised as a concern
Comment on: Cursor Introduces Composer 2.5ID dc-38 \| Developer Communities	news.ycombinator.com/item?id=48195203	smnscu, Hacker News commenterself-described: Personal development	Individual practitioner	Published May 19, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Developer Experience: Mixed or negative Reliability: Raised as a concern
Comment on: Gemini 3.5 FlashID dc-39 \| Developer Communities	news.ycombinator.com/item?id=48200994	lern_too_spel, Hacker News commenterself-described: Personal account, small project	Individual practitioner	Published May 19, 2026	Assessment reviewed Nov 1, 2026	Current	Overall signal Quotas & Plan Changes: Raised as a concern
Comment on: A History of IDEs at GoogleID dc-36 \| Developer Communities	news.ycombinator.com/item?id=48130561	mcoliver, Hacker News commenter, Workspace administratorself-described: Moving their organization off the Workspace AI Ultra add-on	Very small team	Published May 14, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern Product Direction: Raised as a concern
Comment on: AlphaEvolve: Gemini-powered coding agent scaling impact across fieldsID dc-35 \| Developer Communities	news.ycombinator.com/item?id=48062382	jatora, Hacker News commenterself-described: Personal use of several agents	Individual practitioner	Published May 8, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Model Access: Positive Reliability: Raised as a concern Permissions & Safety: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Using coding assistance tools to revive projects you never were going to finishID dc-34 \| Developer Communities	news.ycombinator.com/item?id=47922881	saidinesh5, Hacker News commenterself-described: Weekend home-automation projects	Individual practitioner	Published Apr 27, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Positive Faster on directed work
Comment on: Google is building a Claude Code challenger, Sergey Brin is involvedID dc-33 \| Developer Communities	news.ycombinator.com/item?id=47897605	jdw64, Hacker News commenterself-described: Subscribes to several AI tools	Individual practitioner	Published Apr 25, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Reliability: Raised as a concern Product Direction: Raised as a concern
Comment on: Claude Code to be removed from Anthropic's Pro plan?ID dc-31 \| Developer Communities	news.ycombinator.com/item?id=47862826	mark_l_watson, Retired developer and authorself-described: Personal open-source projects	Individual practitioner	Published Apr 22, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Model Access: Positive Value for Money: Mixed or negative Quotas & Plan Changes: Discussed without concern
Comment on: Our eighth generation TPUs: two chips for the agentic eraID dc-32 \| Developer Communities	news.ycombinator.com/item?id=47864079	WarmWash, Hacker News commenterself-described: Personal tax return test and small greenfield projects	Individual practitioner	Published Apr 22, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Requires Strong Review: Raised as a concern Works best on bounded tasks How does Antigravity compare with the other coding agents engineers use?: Behind
Prompt Injection leads to RCE and Sandbox Escape in AntigravityID ld-03 \| Engineering Blogs & Reviews	www.pillar.security/blog/prompt-injection-leads-to-rce-and-sandbox-escape-in-antigravity	Dan Lisichkin, security researcher at Pillar SecurityPillar Research team testing agentic IDEs for sandbox bypasses	Professional team	Published Apr 20, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Permissions & Safety: Raised as a concern
Antigravity servers down for over 7 hours!ID dc-30 \| Developer Communities	discuss.ai.google.dev/t/antigravity-servers-down-for-over-7-hours/139906	Ill_indication, Freelance developer building for clientsself-described: Client work	Individual practitioner	Published Apr 15, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Reliability: Raised as a concern
Using OpenCode as a fallback agent for AntigravityID ir-14 \| Engineering Blogs & Reviews	dev.to/gdg/using-opencode-as-a-fallback-agent-for-antigravity-37oo	Alexander Tyutin, automation practitionerself-described: Daily delivery work	Individual practitioner	Published Apr 15, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Not counted. Its author co-organizes GDG Almaty, a Google Developer Groups community Google runs.
Comment on: Pro Max 5x quota exhausted in 1.5 hours despite moderate usageID dc-27 \| Developer Communities	news.ycombinator.com/item?id=47739670	Achshar, Hacker News commenter, Google AI Ultra subscriberself-described: Personal development	Individual practitioner	Published Apr 12, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Developer Experience: Positive Quotas & Plan Changes: Discussed without concern How does Antigravity compare with the other coding agents engineers use?: Competitive
Comment on: Pro Max 5x quota exhausted in 1.5 hours despite moderate usageID dc-28 \| Developer Communities	news.ycombinator.com/item?id=47739824	rzkyif, Hacker News commenter, Google AI Pro subscriberself-described: Personal ~15k line codebase	Individual practitioner	Published Apr 12, 2026	Assessment reviewed Nov 1, 2026	Out of date	Out of date, counts toward nothing current
Comment on: Pro Max 5x quota exhausted in 1.5 hours despite moderate usageID dc-29 \| Developer Communities	news.ycombinator.com/item?id=47740122	asdfasgasdgasdg, Programmer of twenty yearsself-described: Personal embedded motor-control project	Individual practitioner	Published Apr 12, 2026	Assessment reviewed Nov 1, 2026	Out of date	Out of date, counts toward nothing current
Antigravity: My Approach to Deliver the Most Assured Value for the Least MoneyID ir-13 \| Engineering Blogs & Reviews	dev.to/gdg/antigravity-my-approach-to-deliver-the-most-assured-value-for-the-least-money-3iip	Alexander Tyutin, automation practitionerself-described: Delivery workflow with quality gates	Individual practitioner	Published Apr 1, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Not counted. Its author co-organizes GDG Almaty, a Google Developer Groups community Google runs.
Google Antigravity: Secret Quota Cuts, Break Trust & Make It Unusable for ProductionID dc-26 \| Developer Communities	discuss.ai.google.dev/t/google-antigravity-secret-quota-cuts-break-trust-make-it-unusable-for-production/136147	aaron_wu, Aaron Wu, long-time paying userself-described: Production work, upgraded from Pro to Ultra	Individual practitioner	Published Mar 26, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern Product Direction: Raised as a concern
[Ultra] Dramatic quota reduction after update: this needs an official explanationID dc-25 \| Developer Communities	discuss.ai.google.dev/t/ultra-dramatic-quota-reduction-after-update-this-needs-an-official-explanation/135526	Mariano Abad, Google AI Ultra subscriberself-described: Several agents running complex tasks in parallel	Individual practitioner	Published Mar 23, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern How much work should Antigravity complete before a human checkpoint?: Broader delegation
Testing Antigravity: Building a Data-Intensive POC at 300km/hID ir-12 \| Engineering Blogs & Reviews	dev.to/gde/testing-antigravity-building-a-data-intensive-poc-at-300kmh-4c57	Patricio Navarro, data engineer and Google Developer Expertself-described: GCP data pipeline prototype	Individual practitioner	Published Mar 22, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Not counted. Its author is a Google Developer Expert, a program Google runs.
Comment on: Google Antigravity IDE rug pulls its quotasID dc-24 \| Developer Communities	news.ycombinator.com/item?id=47344111	riversflow, Hacker News commenter, Google AI Pro subscriberself-described: Personal building on a Pro subscription	Individual practitioner	Published Mar 11, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern
Comment on: Agentic Engineering PatternsID dc-23 \| Developer Communities	news.ycombinator.com/item?id=47266985	jpadkins, Hacker News commenterself-described: Hobby game development	Individual practitioner	Published Mar 5, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Plans & Artifacts: Positive Works best on bounded tasks
Comment on: Agentic Engineering PatternsID dc-22 \| Developer Communities	news.ycombinator.com/item?id=47244874	maccard, Hacker News commenterself-described: Personal evaluation	Individual practitioner	Published Mar 4, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern Reliability: Raised as a concern Needs Close Steering: Raised as a concern
Comment on: Beta Player: unofficial Bandcamp desktop and mobile player with remote controlID dc-21 \| Developer Communities	news.ycombinator.com/item?id=47237309	eremef, Hacker News commenterself-described: Solo open-source app, a month of full-time work	Individual practitioner	Published Mar 3, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern Reliability: Raised as a concern
Comment on: I don't know how you get here from "predict the next word"ID dc-20 \| Developer Communities	news.ycombinator.com/item?id=47163682	measurablefunc, Hacker News commenterself-described: Personal Rust compiler and VM project	Individual practitioner	Published Feb 26, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern Requires Strong Review: Raised as a concern Needs Close Steering: Raised as a concern How much work should Antigravity complete before a human checkpoint?: Tighter steering
Adding Capacitor to Glif with Antigravity: The Good, The Bad, and The Reality CheckID ir-11 \| Engineering Blogs & Reviews	dev.to/playfulprogramming/adding-capacitor-to-glif-with-antigravity-the-good-the-bad-and-the-reality-check-4pm8	Domenico Tenace, open-source developerself-described: Turning a Nuxt app into a mobile app	Individual practitioner	Published Feb 26, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Mixed or negative Requires Strong Review: Raised as a concern
Unacceptable Antigravity Quotas for Gemini 3.1 Pro: Workflow Completely Blocked!ID dc-19 \| Developer Communities	discuss.ai.google.dev/t/unacceptable-antigravity-quotas-for-gemini-3-1-pro-workflow-completely-blocked/124971	Abisheak_Shill, Abisheak Shill, Google AI Pro subscriberself-described: Next.js redesign for a client project	Individual practitioner	Published Feb 21, 2026	Assessment reviewed Nov 1, 2026	Out of date	Out of date, counts toward nothing current
Comment on: Ask HN: Are you using an agent orchestrator to write code?ID dc-17 \| Developer Communities	news.ycombinator.com/item?id=46999578	nprateem, Hacker News commenterself-described: Solo on a 500k+ line codebase	Individual practitioner	Published Feb 13, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Parallel Agents: Positive Faster on directed work How much work should Antigravity complete before a human checkpoint?: Broader delegation
Comment on: Zed editor switching graphics lib from blade to wgpuID dc-18 \| Developer Communities	news.ycombinator.com/item?id=47009336	mercutio2, Hacker News commenterself-described: Personal feature work	Individual practitioner	Published Feb 13, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Model Access: Positive Developer Experience: Mixed or negative
Comment on: Claude Code is suddenly everywhere inside MicrosoftID dc-16 \| Developer Communities	news.ycombinator.com/item?id=46858863	TheAceOfHearts, Hacker News commenterself-described: Personal agentic coding	Individual practitioner	Published Feb 2, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Reliability: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Google AI Pro Subscription: Antigravity Quota Not Working as Advertised (10-Day Lockout Instead of 5-Hour Reset)ID dc-15 \| Developer Communities	discuss.ai.google.dev/t/google-ai-pro-subscription-antigravity-quota-not-working-as-advertised-10-day-lockout-instead-of-5-hour-reset/118505	SMTH_Gaming, SMTH Gaming, Google AI Pro subscriberself-described: Code analysis of a local repository	Individual practitioner	Published Jan 25, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern
Google Antigravity vs GitHub Copilot: Why I'm Team Antigravity NowID ir-10 \| Engineering Blogs & Reviews	dev.to/playfulprogramming/google-antigravity-vs-github-copilot-why-im-team-antigravity-now-fco	Domenico Tenace, open-source developerself-described: Refactoring their Easy Kit Utils library	Individual practitioner	Published Jan 23, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Positive Plans & Artifacts: Positive How does Antigravity compare with the other coding agents engineers use?: Competitive Is Antigravity the team's main coding tool, or one beside another?: Main tool
Comment on: Ask HN: Do you have any evidence that agentic coding works?ID dc-13 \| Developer Communities	news.ycombinator.com/item?id=46700274	defatigable, Hacker News commenterself-described: Personal Chrome extension; uses Augment at work	Individual practitioner	Published Jan 21, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Parallel Agents: Positive Needs Close Steering: Discussed without concern Faster on directed work How much work should Antigravity complete before a human checkpoint?: Tighter steering
Comment on: Ask HN: Do you have any evidence that agentic coding works?ID dc-14 \| Developer Communities	news.ycombinator.com/item?id=46702093	Kerrick, Hobbyist Rubyistself-described: Solo open-source library, built in public	Individual practitioner	Published Jan 21, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Faster on directed work
Antigravity broken: getting only "Agent execution terminated due to error."ID dc-12 \| Developer Communities	discuss.ai.google.dev/t/antigravity-broken-getting-only-agent-execution-terminated-due-to-error/115443	Etienne, Google AI Ultra subscriberself-described: Daily development on macOS	Individual practitioner	Published Jan 15, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Reliability: Raised as a concern
Vibe Mapping: Google's Antigravity is pretty damn amazingID ir-09 \| Engineering Blogs & Reviews	flower.codes/2026/01/15/antigravity.html	Zachary Flower, developerself-described: Hobby tool for a MUD codebase	Individual practitioner	Published Jan 15, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Positive Faster on directed work
Comment on: What happened to WebAssemblyID dc-11 \| Developer Communities	news.ycombinator.com/item?id=46553072	neomantra, Hacker News commenterself-described: Open-source MCP server project	Individual practitioner	Published Jan 9, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Positive Faster on directed work
AudioNoise READMEID ir-08 \| Engineering Blogs & Reviews	github.com/torvalds/AudioNoise/blob/main/README.md	Linus Torvalds, creator of Linuxself-described: Personal audio effects project	Individual practitioner	Published Jan 9, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Listed, no finding position
Comment on: How Google got its groove back and edged ahead of OpenAIID dc-09 \| Developer Communities	news.ycombinator.com/item?id=46537782	mythz, Hacker News commenterself-described: Solo, full-time development	Individual practitioner	Published Jan 8, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Model Access: Positive Value for Money: Positive Quotas & Plan Changes: Discussed without concern Reliability: Discussed without concern Is Antigravity the team's main coding tool, or one beside another?: Main tool
Comment on: How Google got its groove back and edged ahead of OpenAIID dc-10 \| Developer Communities	news.ycombinator.com/item?id=46539556	jchw, Hacker News commenterself-described: Personal Rust projects	Individual practitioner	Published Jan 8, 2026	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Multi-Step Execution: Positive How much work should Antigravity complete before a human checkpoint?: Broader delegation
Comment on: Ask HN: Any example of successful vibe-coded product?ID dc-08 \| Developer Communities	news.ycombinator.com/item?id=46486413	alwinaugustin, Hacker News commenterself-described: Solo, shipping small SaaS apps	Individual practitioner	Published Jan 4, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal How does Antigravity compare with the other coding agents engineers use?: Behind Is Antigravity the team's main coding tool, or one beside another?: Second tool
Comment on: Ask HN: Any example of successful vibe-coded product?ID dc-07 \| Developer Communities	news.ycombinator.com/item?id=46474573	contractorwolf, Software engineerself-described: Solo, consumer app MVP	Individual practitioner	Published Jan 3, 2026	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Positive Faster on directed work
How Google’s Antigravity IDE Changed My Perspective on Small-Team Software DevelopmentID ld-01 \| Engineering Blogs & Reviews	justlandedjets.com/blog/how-google-s-antigravity-ide-changed-my-perspective-on-small-team-software-development	Steve Sink, VP of Technology at Just Landed Jetsself-described: Private jet charter broker with a small team and one lead developer who deploys internal models	Technical leadership	Published Dec 23, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Positive Plans & Artifacts: Positive Requires Strong Review: Discussed without concern Faster on directed work
Antigravity feels heavy and Claude Skills are lightID ir-07 \| Engineering Blogs & Reviews	quesma.com/blog/claude-skills-not-antigravity/	Piotr Migdał, Quesmaself-described: Side-by-side test against Claude Code	Individual practitioner	Published Dec 16, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Model Access: Positive Developer Experience: Mixed or negative Quotas & Plan Changes: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: AI agents are starting to eat SaaSID dc-06 \| Developer Communities	news.ycombinator.com/item?id=46268696	scotty79, Hacker News commenterself-described: Solo, one-evening tool build	Individual practitioner	Published Dec 15, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Positive Requires Strong Review: Raised as a concern Needs Close Steering: Raised as a concern How much work should Antigravity complete before a human checkpoint?: Tighter steering
AI IDE prompt Injection: Reading browser local storageID ir-06 \| Engineering Blogs & Reviews	introvertmac.wordpress.com/2025/12/15/ai-ide-prompt-injection-reading-browser-local-storage/	Manish, independent security researcherself-described: Personal security testing	Individual practitioner	Published Dec 15, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Permissions & Safety: Raised as a concern
This blog is now on Astro thanks to Antigravity!ID ir-05 \| Engineering Blogs & Reviews	hartenfeller.dev/blog/blog-is-now-astro	Philipp Hartenfeller, Product Lead at United Codesself-described: Personal blog migration	Individual practitioner	Published Dec 8, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Multi-Step Execution: Positive Faster on directed work
Google Antigravity Security: The Zero-Click Exfiltration Google Won’t FixID ld-07 \| Engineering Blogs & Reviews	repello.ai/blog/google-antigravity-security	Aaryan Bhujang, AI security researcher at Repello AIAI security company red teaming coding agents	Professional team	Published Nov 28, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Permissions & Safety: Raised as a concern
Antigravity's Gemini ProblemID ir-04 \| Engineering Blogs & Reviews	dev.amitgawande.com/2025/antigravity-problem	Amit Gawande, developerself-described: Standard agentic-IDE test against Claude Code	Individual practitioner	Published Nov 26, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Plans & Artifacts: Positive Quotas & Plan Changes: Raised as a concern Data Privacy: Discussed without concern How does Antigravity compare with the other coding agents engineers use?: Behind
Google Antigravity Exfiltrates DataID ir-03 \| Engineering Blogs & Reviews	www.promptarmor.com/resources/google-antigravity-exfiltrates-data	PromptArmor, AI security research teamself-described: Security team testing Antigravity against prompt injection	Professional team	Published Nov 25, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Browser Verification: Mixed or negative Permissions & Safety: Raised as a concern
Forced Descent: Google Antigravity Persistent Code Execution VulnerabilityID ld-02 \| Engineering Blogs & Reviews	mindgard.ai/blog/google-antigravity-persistent-code-execution-vulnerability	Aaron Portnoy, Chief Product Officer at MindgardAI security company testing Antigravity's workspace trust model	Professional team	Published Nov 25, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Permissions & Safety: Raised as a concern
Comment on: Nano Banana ProID dc-05 \| Developer Communities	news.ycombinator.com/item?id=46004249	elevatortrim, Hacker News commenterself-described: Company weighing a move from Claude to Gemini for agentic coding and employee use	Very small team	Published Nov 21, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Quotas & Plan Changes: Raised as a concern
Using Antigravity for Statistical Physics in JavaScriptID ir-02 \| Engineering Blogs & Reviews	christopherkrapu.com/blog/2025/antigravity-stat-mech/	Christopher Krapu, data scientistself-described: Personal visualization test	Individual practitioner	Published Nov 21, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Browser Verification: Positive Faster on directed work
Comment on: Google AntigravityID dc-03 \| Developer Communities	news.ycombinator.com/item?id=45980543	sega_sai, Hacker News commenter, Gemini Pro subscriberself-described: Personal trial	Individual practitioner	Published Nov 19, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Quotas & Plan Changes: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Comment on: Building more with GPT-5.1-Codex-MaxID dc-04 \| Developer Communities	news.ycombinator.com/item?id=45984011	timtimmy, Hacker News commenterself-described: Evaluating Antigravity for a team codebase	Very small team	Published Nov 19, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Data Privacy: Raised as a concern
Comment on: Google AntigravityID dc-01 \| Developer Communities	news.ycombinator.com/item?id=45972498	Yeroc, Hacker News commenterself-described: Personal trial; only Claude Code is approved at work	Individual practitioner	Published Nov 18, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Plans & Artifacts: Positive Parallel Agents: Positive
Comment on: Google AntigravityID dc-02 \| Developer Communities	news.ycombinator.com/item?id=45972907	Topfi, Hacker News commenterself-described: Personal trial on launch day	Individual practitioner	Published Nov 18, 2025	Assessment reviewed Nov 1, 2026	Needs a recheck	Overall signal Browser Verification: Mixed or negative Reliability: Raised as a concern Data Privacy: Raised as a concern How does Antigravity compare with the other coding agents engineers use?: Behind
Google AntigravityID ir-01 \| Engineering Blogs & Reviews	simonwillison.net/2025/Nov/18/google-antigravity/	Simon Willison, independent developer and bloggerself-described: Personal open-source plugin work	Individual practitioner	Published Nov 18, 2025	Assessment reviewed Nov 1, 2026	Still applicable	Overall signal Plans & Artifacts: Positive Browser Verification: Positive Reliability: Raised as a concern
PlansID pd-01 \| Product Documentation	antigravity.google/docs/plans/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
ModelsID pd-02 \| Product Documentation	antigravity.google/docs/models/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Antigravity in Gemini EnterpriseID pd-03 \| Product Documentation	antigravity.google/docs/enterprise/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Agent permissionsID pd-04 \| Product Documentation	antigravity.google/docs/permissions/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Terminal sandboxID pd-05 \| Product Documentation	antigravity.google/docs/sandbox/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Managing AI credits and quotas (CLI)ID pd-06 \| Product Documentation	antigravity.google/docs/cli/credits/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
IDE extensionsID pd-07 \| Product Documentation	antigravity.google/docs/ide/extensions/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Migrating from Gemini CLIID pd-08 \| Product Documentation	antigravity.google/docs/cli/gcli-migration/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
FAQID pd-09 \| Product Documentation	antigravity.google/docs/faq/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
ChangelogID pd-10 \| Product Documentation	antigravity.google/docs/changelog/	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Google Antigravity Additional Terms of ServiceID pd-11 \| Product Documentation	antigravity.google/terms	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Changes to Antigravity plansID pd-12 \| Product Documentation	antigravity.google/blog/changes-to-antigravity-plans	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Bringing Antigravity to Gemini EnterpriseID pd-13 \| Product Documentation	antigravity.google/blog/antigravity-enterprise	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
AI developer tools overviewID pd-14 \| Product Documentation	docs.cloud.google.com/gemini/enterprise/docs/ai-developer-tools-overview	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Configure AI developer tools settingsID pd-15 \| Product Documentation	docs.cloud.google.com/gemini/enterprise/docs/ai-developer-tools-settings	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Quotas and pay-as-you-go usageID pd-16 \| Product Documentation	docs.cloud.google.com/gemini/enterprise/docs/quotas-and-overages	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only
Gemini Code Assist Standard and Enterprise subscriptionsID pd-17 \| Product Documentation	docs.cloud.google.com/gemini/docs/codeassist/sunset	GoogleOfficial	Not counted (documentation)	No date stated	Documentation checked Oct 12, 2026	Current	Verification only

SuneraX, Antigravity user

Hans, runs a team's AI agents on its own server

joaoviniciusgs, Hacker News commenter

georgemcbay, Long-time OpenSCAD user

tinyhouse, Hacker News commenter, former Pro subscriber

mapontosevenths, Hacker News commenter, Google AI Ultra subscriber

taylorfinley, Hacker News commenter

smartbit, Hacker News commenter

huydotnet, Hacker News commenter

martythemaniak, Hacker News commenter

piyh, Hacker News commenter

Janson79jc, solo developer

parasti, Hacker News commenter

Freya Smith, uses Antigravity for work

flying_manta, Antigravity CLI user

Dhruv Jani, developer

dlahoda, Engineer running a review orchestration on their team's repository

vallerie, Hacker News commenter

evilduck, Hacker News commenter

rafaelmn, Hacker News commenter

allthetime, Hacker News commenter

Gergely Orosz, author of The Pragmatic Engineer

dpweb, Hacker News commenter, student plan

sanarothe, Non-software engineer

dan_voronov, Blogger reviewing AI programming tools

leoedin, Hacker News commenter, former subscriber

hn_throw2025, Hacker News commenter, former Cursor subscriber

slaser79, Hacker News commenter

Jesus Padilla Soqui, Straiker STAR team

Tanaike, Google Developer Expert

qlte, Hacker News commenter, Google AI Pro subscriber

malkamius, Hacker News commenter

dudeinhawaii, Hacker News commenter, former Google AI Ultra subscriber

tobias2014, Hacker News commenter

stonewhite, Hacker News commenter buying AI tools for their company

mythz, Hacker News commenter

mwryl, Hacker News commenter

Rohan Soni, Google, writing Inspired Entertainment's case study with its CTO

Dan Lisichkin, security researcher at Pillar Security

Andrey Lukyanenko, ML engineer and Google Developer Expert

SwellJoe, Developer building a security auditing harness

Christopher Tuz, AI security researcher on the STAR Labs team at Straiker

yogendra6698, Builds AI agents professionally

moshegramovsky, Hacker News commenter

anigbrowl, Hacker News commenter

trollbridge, Hacker News commenter running a small development shop

linsomniac, Hacker News commenter

bjackman, Hacker News commenter

polotics, Hacker News commenter

evilturnip, Hacker News commenter

seabrookmx, Hacker News commenter

mark_l_watson, Retired developer and author

heyyeah, Hacker News commenter

u8, Developer of CLI developer tooling

daft_pink, Hacker News commenter

spankalee, Hacker News commenter

Joske Vermeulen, runs an autonomous agent startup race

Jason Agostoni, developer and author of the Ship Bench benchmark

ModelRift engineering team

Sid, independent developer on Google AI Ultra

Madhur Mishra, Antigravity user

MisterPea, Hacker News commenter

No1, Hacker News commenter

tegeek, Hacker News commenter

cft, Hacker News commenter, Google AI Pro subscriber

almog, Hacker News commenter, Google AI Pro subscriber

Vicente Cortes, Google One Pro subscriber for over a year

smnscu, Hacker News commenter

lern_too_spel, Hacker News commenter

mcoliver, Hacker News commenter, Workspace administrator

jatora, Hacker News commenter

saidinesh5, Hacker News commenter

jdw64, Hacker News commenter

mark_l_watson, Retired developer and author

WarmWash, Hacker News commenter

Dan Lisichkin, security researcher at Pillar Security

Ill_indication, Freelance developer building for clients

Alexander Tyutin, automation practitioner

Achshar, Hacker News commenter, Google AI Ultra subscriber

rzkyif, Hacker News commenter, Google AI Pro subscriber