Skip to main content
Zed 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.

Whose sources count

Source

95 sources in All practitioners, with product documentation Showing all 95 sources

  1. Mixed

    Kang Cahya Keren, developer and blogger

    Post on X by Kang Cahya KerenPost on X

    Zed frequently freezes when they use ChatGPT models through the Zed Agent.

    Published Oct 16, 2026self-described: Moved to Zed from VS Code and Antigravity

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Observed on ChatGPT
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-10-16, ChatGPT
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relevance

    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

  2. Negative

    Nenad Novakovic, founder

    Post on X by Nenad NovakovicPost on X

    Asks why ACP output in Zed looks worse than what the Claude Code app shows.

    Published Oct 9, 2026self-described: Founder building his own apps

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-10-09
    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
    Technical leadership
    Evidence
    Reported
    Applies to
    Still applicable

  3. Positive

    Jacob Wolf, leads podcasts and integrations engineering at beehiiv

    Post on X by Jacob WolfPost on X

    Uses Zed as an agent-agnostic control plane, which makes switching between OpenCode, Cursor, and Claude Code by task easy.

    Published Oct 7, 2026self-described: Engineering lead switching between OpenCode, Cursor, and Claude Code

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-10-07
    Counts toward
    Operational control, models and deployment: favorable, G1 (1 unit before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Still applicable

  4. Positive

    Eluert Mukja, full-stack developer

    Post on X by Eluert MukjaPost on X

    Runs most of their coding through agent threads in Zed and built a phone app that mirrors the agent panel.

    Published Oct 4, 2026self-described: Built a phone companion for Zed's agent panel

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-10-04
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit 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

  5. Positive

    jackjeff, developer using Zed with devcontainers

    Comment on: Zed and devcontainersHacker News comment

    Uses devcontainers with editors including Zed, describing the setup as straightforward when the project contains its required tools.

    Published Oct 3, 2026self-described: Zed and devcontainers for a development environment

    Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-10-03
    Counts toward
    Adoption and upkeep, setup: favorable, G2 (2 units before bounds)

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  6. Mixed

    rodesia, solo builder of a web platform

    Post on X by rodesiaPost on X

    Was using Zed for a while and "still love it", but a few weeks ago realized only the AI agent pane was in use, and is now "pretty much full-time" in Claude Code in the terminal.

    Published Oct 2, 2026self-described: Building and running a web platform alone

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-10-02
    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

  7. Positive

    Chris Reynolds, IT Director

    Post on X by Chris ReynoldsPost on X

    Runs Zed with a local model for next-edit prediction.

    Published Sep 25, 2026self-described: IT director using Zed and Sublime as minimal editors

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-09-25
    Counts toward
    Operational control, models and deployment: favorable, G1 (1 unit before bounds)

    Checked Oct 29, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Still applicable

  8. Positive

    Aris (riipandi), developer on X

    Post on X by ArisPost on X

    Wants to turn off every AI feature except edit prediction, which they really like.

    Published Sep 25, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, from a competitor's side How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Competitor staff: not counted as independent; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    competitor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-09-25
    Not counted
    Operational control, execution control: excluded, criticism from a competitor's side, kept as an attributed position

    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

  9. Negative

    Mike McQuaid, CTPO at Administrate

    Vibe Coding Developer Productivity ToolsBlog post, mikemcquaid.com

    McQuaid has almost entirely replaced Zed with AgentIDE, a sandboxed agent app he built for Codex and Claude Code sessions that a few coworkers and Homebrew maintainers now use.

    "…now completely off Superset and almost entirely off Fork and Zed by (vibe) building my own tool…"
    Excerpt, Mike McQuaid

    Published Sep 24, 2026Built AgentIDE for his own agent workflow; coworkers at Administrate and Homebrew maintainers use it

    Practitioner account, self-described; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Used it directly
    Role
    Name self-described; employer self-described; role self-described (CTPO)
    Relationship
    customer (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-09-24
    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

    Published on
    Engineering Blogs & Reviews
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Current

  10. Positive

    emerongi, engineer reviewing Zed's collaborative agent workflow

    Comment on: Zed collaborative agent workflowHacker News comment

    Sees a useful review loop in which a coworker inspects an agent thread directly and needs no explanation from its author, though they want polished final output.

    Published Sep 18, 2026self-described: Response to a video of Zed collaborative review

    Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Opinion
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-09-18
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  11. Negative

    Andrey Tarantsov, Technical director at Bubblehouse

    Post on X by Andrey TarantsovPost on X

    Likes Zed's UI touches but says Codex and Grok Build over ACP still fall short: no UI for subagent threads and full file dumps in the agent panel.

    Published Sep 18, 2026self-described: Technical director trying Codex and Grok Build as external agents

    Practitioner account, pseudonymous; direct use; counts toward Reliability, Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Used it directly
    Support
    1 artifact (issue)
    Date and version
    2026-09-18
    Counts toward
    Adoption and upkeep, setup: unfavorable, G2 (2 units before bounds)
    Counts toward
    Reliability, run stability: 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
    Technical leadership
    Evidence
    Reported
    Applies to
    Still applicable

  12. No opinion stated

    NortySpock, developer evaluating Zed's default prompt

    Comment on: Zed prompt overheadHacker News comment

    Has looked at Zed editor's default prompt and thought "I hope this is worth the 7k tokens it costs me every session", and suggests "perhaps" the takeaway is to beware overly long prompts and keep the system prompt relevant to the field of work.

    Published Sep 17, 2026self-described: Zed editor prompt overhead

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-09-17
    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

  13. Positive

    jackjeff, developer evaluating Zed's agent workflow

    Comment on: trying Zed againHacker News comment

    After retrying Zed, the developer found review features let them do roughly what they could in Cursor.

    Published Aug 29, 2026self-described: Retesting Zed after an earlier 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 Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    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
    Still applicable

  14. Mixed

    faisal-fida, GitHub issue author

    Cannot resume/open an existing Claude Code session in Zed when it is running as a background agent (works in VS Code)GitHub issue

    A Claude Code session running as a background agent fails to open in Zed with a raw internal error, while the same session opens in VS Code.

    Published Aug 11, 2026self-described: Claude Code over SSH remote development

    Practitioner account, pseudonymous; structured test; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Ran a structured test; Artifact checked (log); Observed on Zed: v1.15.0+preview.336.05d125a865cbfd8a498278f8e396b22ea554ccaa (Zed Preview)
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile); that is not proof none exists
    How they know
    Ran a structured test
    Support
    1 artifact (log)
    Date and version
    2026-08-11, Zed: v1.15.0+preview.336.05d125a865cbfd8a498278f8e396b22ea554ccaa (Zed Preview)
    Counts toward
    Reliability, run stability: unfavorable, G3 (3 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

  15. Mixed

    xbt573, GitHub issue author

    External agents are unavailable in shared projects while in CollaborationGitHub issue

    In a shared collaboration project, only the Zed Agent is offered; Claude Code and the terminal agent are missing.

    Published Jul 20, 2026self-described: Using a shared project in a Zed collaboration channel

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Observed on v1.10.3+stable.324.0c54c414d522234de7298039708ffe85a116892a
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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 (screenshot)
    Date and version
    2026-07-20, v1.10.3+stable.324.0c54c414d522234de7298039708ffe85a116892a
    Counts toward
    Operational control, models and deployment: unfavorable, 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
    Observed on
    Zed v1.10.3 on Windows

  16. Positive

    Peter Thomson, CTO at Icehouse Ventures

    Post on X by Peter ThomsonPost on X

    Thomson's team keeps a low-AI editor such as Zed installed beside full-agent daily drivers like Cursor and Codex, and switches to it for code review and hand-written code.

    "One thing our team does to stay sharp is have at least one "low ai" editor installed, could be Sublime, Zed, Php Storm, or VS Code with plugins disabled."
    Excerpt, Peter Thomson

    Published Jun 22, 2026Icehouse Ventures engineering team, which keeps full-agent tools as daily drivers

    Practitioner account, name and role on their organization's own page; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Name and role on their organization's own page; No tie to Zed found in GILD's check; Opinion
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Opinion, no use stated
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-06-22
    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

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Current

  17. Mixed

    slopinthebag, Hacker News commenter

    Comment on: Software is made between commitsHacker News comment

    Likes the inline assistant and an agent that stays out of the way, but dislikes the push toward an agent-first layout.

    Published Jun 11, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-06-11
    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
    Still applicable

  18. Positive

    arc (arcbjorn), agent systems and ML engineer

    Post on X by arcPost on X

    Says Zed's own thread implementation and its screen for concurrent agents put it level with the best agentic editors.

    Published May 30, 2026self-described: Zed user since the 2022 private beta

    Practitioner account, pseudonymous; direct use; not counted, tied to the vendor How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Zed partner: not counted as independent; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    program member (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-05-30
    Not counted
    Adoption and upkeep, setup: excluded, praise from someone tied to the vendor, kept as an attributed position
    Not counted
    Adoption and upkeep, continuity: 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

    Counts toward

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  19. Mixed

    jordandakota, GitHub issue author

    Claude Code ACP session enters unrecoverable state after hitting usage limitGitHub issue

    After a Claude usage limit, the ACP session stays alive but silently drops prompts until the thread or Zed restarts.

    Published May 2, 2026self-described: Claude Code over ACP on a Claude plan with usage limits

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Observed on v1.0.0+stable.257.5ec84a926ef83865afb92d2a3d1ca3b419572cf9
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-05-02, v1.0.0+stable.257.5ec84a926ef83865afb92d2a3d1ca3b419572cf9
    Counts toward
    Reliability, run stability: unfavorable, 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

  20. Negative

    zephod, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Loved Zed for a few days but went back to Cursor because they depend on Cursor Tab; Zed AI, Copilot, and Mercury all felt forgetful beside it.

    Published Apr 30, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-30
    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
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  21. Mixed

    presentation, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Ran the Cursor agent through ACP and found it markedly worse than in Cursor itself, with adding context and reviewing changes clumsier too.

    Published Apr 30, 2026self-described: Developer whose company pays for Cursor

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes, Reliability, Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; 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
    2026-04-30
    Counts toward
    Delivered outcomes, correctness: unfavorable, G2 (2 units before bounds)
    Counts toward
    Reliability, run stability: unfavorable, G2 (2 units before bounds)
    Counts toward
    Adoption and upkeep, setup: unfavorable, 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

  22. Negative

    matthewtse, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Found Zed's tab completion unusable next to Cursor's and will try again only if it improves.

    Published Apr 30, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-30
    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

  23. Positive

    recov, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Likes Claude over ACP for keeping the code on screen while chatting; terminal-only work feels like a handicap.

    Published Apr 29, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-29
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  24. Mixed

    sodacanner, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Claude Code in Zed works but lacks sub-agent display, context clearing, a usage display, and effort control, so they went back to the terminal.

    Published Apr 29, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-29
    Counts toward
    Operational control, models and deployment: 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
    Still applicable

  25. Positive

    NortySpock, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Came to Zed because a local Ollama model took a dropdown to set up, then moved to OpenRouter models with a dropdown and an API key.

    Published Apr 29, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; counts toward Operational control, Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-29
    Counts toward
    Adoption and upkeep, setup: favorable, G2 (2 units before bounds)
    Counts toward
    Operational control, models and deployment: 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

  26. Mixed

    JnnydevDude, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Enjoys Zed, and the one sore point is an integration with Claude Code that is not smooth.

    Published Apr 29, 2026self-described: Light Zed user for a few months

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-29
    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

  27. Positive

    jeppester, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Uses Claude Code in Zed a lot: it lacks many features but feels less busy than the terminal, and it improves with each release.

    Published Apr 29, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-29
    Not counted
    Adoption and upkeep, continuity: 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

  28. Positive

    mlsu, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Likes Zed's AI-assisted setup and thinks a file review pane inside the editor is the right UX for AI tools.

    Published Apr 29, 2026self-described: Developer new to Zed on a mixed C and Rust project

    Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-29
    Counts toward
    Adoption and upkeep, setup: 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

  29. Mixed

    scottmessinger, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Is excited about multi-agent support but finds it confusing which of the agent sidebar and the titlebar controls the worktree and branch.

    Published Apr 29, 2026self-described: Zed user for years

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-29
    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

  30. Mixed

    ksajadi, Hacker News commenter

    Comment on: Zed 1.0Hacker News comment

    Likes the ACP approach, but finds it buggy and limited: no editing of earlier messages, and work that occasionally never ends.

    Published Apr 29, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-29
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  31. Positive

    Omar McAdam, CTO at Different AI

    Post on X by Omar McAdamPost on X

    McAdam switched to Zed as his IDE while OpenCode writes the code, and uses Zed to clean up code and review large files and plans, calling it clean and light.

    "…switched to Zed as my ide @opencode writes everything Zed is for cleaning up code, reviewing large files/plans…"
    Excerpt, Omar McAdam

    Published Apr 29, 2026CTO of Different AI, which builds OpenWork, with OpenCode as his coding agent

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-04-29
    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

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Current

  32. Mixed

    0xSero, developer on X

    Post on X by 0xSeroPost on X

    Likes Zed for reading code with the new agent mode, but wants the ACP panel to link to files and lines and work more tightly with the codebase.

    Published Apr 26, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Competitor staff: not counted as independent; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    sponsor (self disclosed); sponsor (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-04-26
    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

  33. Negative

    tankmohit11, Hacker News commenter

    Comment on: Parallel agents in ZedHacker News comment

    Uninstalled Zed over the agent UI: tiny, vague icons and an x that closes the editor, an agent, or a panel unpredictably.

    Published Apr 23, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-23
    Counts toward
    Operational control, models and deployment: 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
    Still applicable
    Observed on
    Parallel agents release

  34. Positive

    jamie_ca, Hacker News commenter

    Comment on: Parallel agents in ZedHacker News comment

    Is buying into parallel threads in worktrees and wants lifecycle hooks to set up and tear down databases per worktree.

    Published Apr 22, 2026self-described: Developer whose employer provides GitHub Copilot

    Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; 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
    2026-04-22
    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
    Parallel agents release

  35. Mixed

    verse, Hacker News commenter

    Comment on: Parallel agents in ZedHacker News comment

    Uses Zed daily but dislikes a default layout that pushes code and the file tree aside for AI tools, and expects it to turn new users away.

    Published Apr 22, 2026self-described: Daily Zed user

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    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
    Agentic default layout

  36. Mixed

    lfx, Hacker News commenter

    Comment on: Parallel agents in ZedHacker News comment

    With Claude Code, Gemini CLI, and Codex in the terminal, Zed feels less relevant, and Neovim feels more natural.

    Published Apr 22, 2026self-described: Zed user for over a year

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    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

  37. Mixed

    conqrr, Hacker News commenter

    Comment on: Parallel agents in ZedHacker News comment

    Loves Zed with OpenRouter at home but finds its Claude Code integration weak next to the Zed Agent with a Claude model, so uses VS Code with Claude Code at work.

    Published Apr 22, 2026self-described: Developer using Zed at home and Claude Code at work

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    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

  38. Positive

    Mike McQuaid, CTPO at Administrate

    Sandboxes and Worktrees: My secure Agentic AI SetupBlog post, mikemcquaid.com

    McQuaid runs Codex and Claude Code in sandboxed worktrees and edits their output in Zed, his editor of choice, picked for startup speed because he no longer needs Cursor's better autocomplete.

    "I picked Zed because I spend less time in my editor now, don’t need Cursor’s better autocomplete and care more about startup speed…"
    Excerpt, Mike McQuaid

    Published Apr 14, 2026Runs sandboxed Codex and Claude Code agents on Homebrew and Administrate repositories

    Practitioner account, self-described; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Competitor staff: not counted as independent; Used it directly
    Role
    Name self-described; employer self-described; role self-described (CTPO)
    Relationship
    former vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-04-14
    Not counted
    no aspect: excluded, takes no position on any assessed aspect

    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
    Current

  39. No opinion stated

    kisamoto (Ewan), author of the Braw.dev post under discussion

    Comment on: Reallocating $100/Month Claude Code Spend to Zed and OpenRouterHacker News comment

    Says that "sadly Zed seems to add 10%", so it is still more worthwhile to use OpenRouter, and that it is "perhaps" more worthwhile to stay solely on Cursor with the limited models.

    Published Apr 9, 2026self-described: Developer moving a US$100 per month Claude Code budget to Zed and OpenRouter

    Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Opinion; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-09
    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
    Still applicable

  40. Mixed

    philipp-gayret, Hacker News commenter

    Comment on: Reallocating $100/Month Claude Code Spend to Zed and OpenRouterHacker News comment

    Uses Zed but warns that Claude Code hooks do not work in Zed's integration, so heavy hook users should stay in the terminal.

    Published Apr 9, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-04-09
    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

  41. Mixed

    avilay, Hacker News commenter

    Comment on: Reallocating $100/Month Claude Code Spend to Zed and OpenRouterHacker News comment

    Found Zed more responsive than VS Code and loved the Zed Agent autocomplete, then went back to VS Code over a debugger bug.

    Published Apr 9, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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 (issue)
    Date and version
    2026-04-09
    Counts toward
    Delivered outcomes, task completion: unfavorable, 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

  42. Positive

    Ewan (kisamoto on Hacker News), author of Braw.dev

    Reallocating $100/Month Claude Code spend to Zed and OpenRouterBlog post, Braw.dev

    Pays US$10 a month for Zed and routes models through OpenRouter, because Zed's hosted token prices run above the providers' own API prices.

    Published Apr 6, 2026self-described: Developer moving a US$100 per month Claude Code budget to Zed and OpenRouter

    Practitioner account; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Customer of Zed; Used it directly; Specific details
    Role
    Name unknown; employer unknown; role unknown
    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
    2026-04-06
    Counts toward
    Operational control, models and deployment: mixed, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
    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
    Still applicable
    Observed on
    Zed Pro at US$10 per month with OpenRouter

  43. Mixed

    secondl1ght, GitHub issue author

    All agent actions extremely slowGitHub issue

    Streaming, tool calls, and code generation in the Zed Agent frequently slow to a crawl, where the agent is normally very fast.

    Published Apr 3, 2026self-described: Zed Agent on Linux

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Observed on v0.230.1+stable.210.bf3a14350a4fa4b67747afe2e50128fb8fea4fa3
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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 (recording)
    Date and version
    2026-04-03, v0.230.1+stable.210.bf3a14350a4fa4b67747afe2e50128fb8fea4fa3
    Counts toward
    Reliability, service availability: 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
    Still applicable
    Observed on
    Zed v0.230.1 on Ubuntu 24.04

  44. Mixed

    princhman, GitHub issue author

    Claude Code ACP increases zed energy consumption 100xGitHub issue

    Starting a Claude ACP thread made Zed's energy use jump about 100 times in Activity Monitor.

    Published Mar 15, 2026self-described: Running the Claude agent over ACP on macOS

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Observed on v0.227.1+stable.199.9f9b707d39d62468d4cdaed2d8eb95a847da4cf9
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-03-15, v0.227.1+stable.199.9f9b707d39d62468d4cdaed2d8eb95a847da4cf9
    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
    Zed v0.227.1

  45. Mixed

    somtooo, GitHub issue author

    GPT-5.3 Codex from copilot provider is unusable in zedGitHub issue

    Reports that GPT-5.3 Codex through the GitHub Copilot provider is unusable in Zed 0.223.5: tool calls often fail, it says it edited files without editing anything, and it stops before doing the work. Other Codex models work well in Zed.

    Published Mar 3, 2026self-described: Using GPT-5.3 Codex from a GitHub Copilot subscription in the Zed Agent

    Practitioner account, pseudonymous; direct use; counts toward Delivered outcomes, Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Observed on Zed: 0.223.5
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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, Zed: 0.223.5
    Counts toward
    Delivered outcomes, task completion: unfavorable, G2 (2 units before bounds)
    Counts toward
    Reliability, run stability: unfavorable, G2 (2 units before bounds)

    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
    Zed 0.223.5, GPT-5.3 Codex through Copilot

  46. Positive

    Quinn Slack, CEO and Member of Technical Staff at Amp

    Post on X by Quinn SlackPost on X

    Slack has fully switched from VS Code to Zed for code editing, with Zed's built-in keystroke commands covering his last missing workflow without an extension from his agent.

    "I've fully switched from VS Code to Zed for my code editing needs."
    Excerpt, Quinn Slack

    Published Feb 14, 2026Runs Amp as his coding agent and Zed as his editor

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Competitor staff: not counted as independent; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    competitor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-02-14
    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

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Current

  47. Negative

    trcf23, Hacker News commenter

    Comment on: Zed editor switching graphics lib from blade to wgpuHacker News comment

    Sees the agent panel panic in longer conversations or stall without proceeding.

    Published Feb 13, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    Reliability, run stability: 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

  48. Positive

    Quinn Slack, CEO and Member of Technical Staff at Amp

    Post on X by Quinn SlackPost on X

    Calls Zed really nice, with awesome simplicity and speed and LSP servers used directly. Amp cutting editor-specific layers such as VS Code extensions led the author to Zed; setting up Amp's codebase took about 30min, and the author will be trying it out this week.

    "But we're reducing our reliance on human-only/in-editor feedback loops in our codebase, because the ones used by agents are more important."
    Excerpt, Quinn Slack

    Published Feb 10, 2026Moving Amp's own codebase toward feedback loops that coding agents use

    Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Competitor staff: not counted as independent; Used it directly; Specific details
    Role
    Pseudonymous account; identity not pursued
    Relationship
    vendor employee (self disclosed); competitor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-02-10
    Counts toward
    Adoption and upkeep, setup: 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
    Technical leadership
    Evidence
    Reported
    Applies to
    Current

  49. Positive

    Stephen Haney, founder of Paper

    Post on X by Stephen HaneyPost on X

    Haney praises the new Claude Code extension in Zed and is testing Zed as his full-time editor.

    "…the new Claude Code extension in Zed is 🔥 I'm testing using Zed full time now…"
    Excerpt, Stephen Haney

    Published Jan 28, 2026Founder of Paper, a design tool company

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-01-28
    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

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Current

  50. Positive

    Abishek_Muthian, Hacker News commenter

    Comment on: I switched from VSCode to ZedHacker News comment

    Moved to Zed for AI: the Claude integration works smoothly, the editor is fast, and any agent can be used when needed.

    Published Jan 6, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-01-06
    Not counted
    Operational control, models and deployment: 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

  51. Positive

    RamblingCTO, Hacker News commenter

    Comment on: I switched from VSCode to ZedHacker News comment

    Happy after switching, though Zed sometimes takes over the CPU and crashed once, which they attribute to Claude Code.

    Published Jan 5, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-01-05
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  52. Positive

    giancarlostoro, Hacker News commenter

    Comment on: I switched from VSCode to ZedHacker News comment

    Is leaving JetBrains because its bundled AI is not worth paying for beside Claude Code, and finds Zed's Claude Code integration richer than JetBrains'.

    Published Jan 5, 2026self-described: Developer leaving a JetBrains subscription after nearly 10 years

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-01-05
    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

  53. Negative

    dmix, Hacker News commenter

    Comment on: I switched from VSCode to ZedHacker News comment

    Tried to move from Cursor and found Zed's LLM integration early, with Cursor far ahead on developer experience and fairly priced models.

    Published Jan 5, 2026self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-01-05
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  54. Positive

    Octoth0rpe, Hacker News commenter

    Comment on: I switched from VSCode to ZedHacker News comment

    Trusts Zed more since its AI plans began, because Pro buys tokens across OpenAI, Anthropic, and Google with a spending cap, which looks like a sustainable business model.

    Published Jan 5, 2026self-described: Early Zed adopter

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Observed on pro
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2026-01-05, pro
    Not counted
    Cost predictability and limits, cost transparency: repeats a stronger account in its group
    Not counted
    Operational control, models and deployment: 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

  55. Positive

    Victor Skvortsov, author of Ten thousand meters

    I switched from VSCode to ZedBlog post, Ten thousand meters

    Left VS Code over intrusive Copilot features. Found Zed fast and responsive, with no stability problems in two weeks. Uses Codex in the CLI for AI work.

    Published Jan 3, 2026self-described: Python and Go developer who uses a CLI agent (Codex) for AI work

    Practitioner account; direct use; counts toward Reliability, Adoption and upkeep 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
    No artifact or independent corroboration recorded
    Date and version
    2026-01-03
    Counts toward
    Reliability, run stability: favorable, G1 (1 unit before bounds), capped: C-relationship, C-unknown-control
    Counts toward
    Adoption and upkeep, setup: mixed, 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
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  56. Positive

    Dhravya Shah, founder of Supermemory

    Post on X by Dhravya ShahPost on X

    Shah recommends Zed with Claude Code or OpenCode as the setup to use.

    "…zed + Claude code / opencode is the move…"
    Excerpt, Dhravya Shah

    Published Jan 3, 2026Founder of Supermemory, a memory layer for AI apps

    Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Opinion
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed found in GILD's check (byline, content disclosure, platform api profile, author profile); that is not proof none exists
    How they know
    Opinion, no use stated
    Support
    No artifact or independent corroboration recorded
    Date and version
    2026-01-03
    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

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Current

  57. Positive

    travisgriggs, Hacker News commenter at a 2-3 person shop

    Comment on: Zed is our officeHacker News comment

    Pays for Zed Pro and likes the integrated agent after five months, while wanting less cognitive load from the editor.

    Published Nov 13, 2025self-described: A 2-3 person shop working across four operating systems and 5+ languages

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Customer of Zed; Used it directly; Observed on pro
    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
    2025-11-13, pro
    Not counted
    Delivered outcomes, context handling: 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
    Still applicable

  58. Mixed

    lukaslalinsky, Hacker News commenter

    Comment on: Codex Is Live in ZedHacker News comment

    A Zed user who says Claude Code in the panel is not really Claude Code: ACP reduces the agents to shared functionality, with very limited context management.

    Published Oct 18, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-10-18, needs a recheck
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  59. Negative

    mcjiggerlog, Hacker News commenter

    Comment on: Codex Is Live in ZedHacker News comment

    Found Codex in Zed slow and unexplained on day one, Claude Code in Zed usable with rough edges, and Cursor still the nicer GUI agent.

    Published Oct 17, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-10-17, needs a recheck
    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, pending a recheck

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Codex over ACP at launch

  60. Negative

    mosselman, Hacker News commenter

    Comment on: Codex Is Live in ZedHacker News comment

    Calls Zed's inline suggestions far behind Cursor's, which follow a file rename into the module name and suggest edits across the file.

    Published Oct 16, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-10-16, needs a recheck
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  61. No opinion stated

    José Valim, Chief Adoption Officer at Dashbit

    A new direction for AI developer tooling featuring José Valim, creator of Tidewave (Changelog & Friends #112)Podcast episode transcript, Changelog & Friends

    Valim uses Zed a lot alongside Tidewave, waiting on their notifications while agents work, and says Tidewave is building on Zed's ACP to talk to Codex, Claude Code and Gemini CLI. Thinks pushing people to build on Claude Code or Codex "like with ACP" is "not actually a bad idea".

    "I actually think pushing people towards using Claude Code more, or Codex, and building on top of those tools, like with ACP, is not actually a bad idea…"
    Excerpt, José Valim

    Published Oct 10, 2025Creator of Elixir, building Dashbit's Tidewave coding agent on ACP

    Practitioner account, name and role on an outside page; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Name and role on an outside page; Competitor staff: not counted as independent; Used it directly; Needs recheck after 12 months
    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 (Chief Adoption Officer at Dashbit)
    Relationship
    vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    No artifact or independent corroboration recorded
    Date and version
    2025-10-10, needs a recheck
    Not counted
    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 31, 2026 under gild-policy/1.0.0. The scorecard

    Counts toward

    Published on
    Talks & Podcasts
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Still applicable

  62. Mixed

    agrippanux, Hacker News commenter

    Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedHacker News comment

    Finds burn mode strong but costly, now runs Claude Code with Neovim, and expects Zed's Claude integration to trail the latest Claude Code.

    Published Sep 24, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Opinion; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-24, needs a recheck
    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

  63. Mixed

    genshii, Hacker News commenter

    Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedHacker News comment

    Pays for Zed Pro only for edit prediction and calls it garbage next to Cursor's, though the 10 to 20% of useful suggestions still justify the subscription.

    Published Sep 24, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Customer of Zed; Used it directly; Needs recheck after 12 months
    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
    2025-09-24, needs a recheck
    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
    Still applicable
    Observed on
    Zed Pro for edit predictions, Claude Code in the terminal

  64. Positive

    WD-42, Hacker News commenter

    Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedHacker News comment

    Expects to save money under token pricing. Keeps paying for Zed to write code themselves; hardcore agentic editing is not the reason.

    Published Sep 24, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-24, Zed Pro, needs a recheck
    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

  65. Mixed

    oakesm9, Hacker News commenter

    Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedHacker News comment

    Accepts the pricing change but says the announcement did not say what the API list prices behind list price plus 10% are.

    Published Sep 24, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Opinion; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-24, pro plan, needs a recheck
    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
    Still applicable

  66. Positive

    pkilgore, Hacker News commenter

    Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedHacker News comment

    As a Claude Max and Zed user, sees costs go down, and wants a plan with edit prediction alone and their own key for the rest.

    Published Sep 24, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-24, needs a recheck
    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

  67. No opinion stated

    sethhochberg, Hacker News commenter buying AI tools for an organization

    Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedHacker News comment

    As a corporate purchaser, says "bring your own key" is "just about the only way" the company can let employees stay close to new tools, since it trusts its corporate-managed OpenAI tenant and its governance and budget controls.

    Published Sep 24, 2025self-described: Corporate purchaser governing employee AI access through a company-managed OpenAI tenant

    Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Opinion; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-24, needs a recheck
    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

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Still applicable

  68. Positive

    hakanensari, Hacker News commenter

    Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedHacker News comment

    Calls delegating to CLI agents in the agent panel the right direction after a month of Claude Code in Zed, with SDK limits still to fix.

    Published Sep 24, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; opinion; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Opinion; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-24, needs a recheck
    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
    Still applicable
    Observed on
    Claude Code over ACP, beta

  69. Mixed

    Alek Dobrohotov, Product Manager at C&C

    Zed + Claude Code: A Beautiful Promise That's Not Quite There YetBlog post, The Vibe Coding Post

    Praises Zed's speed and diff review, but after 30 days of standalone Claude Code finds the beta integration a step back, without Plan Mode, /compact, or subagents.

    Published Sep 6, 2025self-described: Builds internal tools for retail, education, and B2B teams at C&C, an Apple Premium Partner

    Practitioner account, self-described; direct use; counts toward Delivered outcomes, Reliability, Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Self-described; Used it directly; Specific details; Needs recheck after 12 months
    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
    1 artifact (repository)
    Date and version
    2025-09-06, needs a recheck
    Counts toward
    Delivered outcomes, context handling: unfavorable, G1 (1 unit before bounds), capped: C-relevance, C-relationship
    Counts toward
    Delivered outcomes, task completion: unfavorable, G1 (1 unit before bounds), capped: C-relationship
    Counts toward
    Reliability, run stability: favorable, G1 (1 unit before bounds), capped: C-relationship
    Counts toward
    Operational control, models and deployment: favorable, G2 (2 units before bounds), capped: C-relationship
    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

    Published on
    Developer Communities
    Who
    Professional team
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Claude Code over ACP, beta

  70. Positive

    chillfox, Hacker News commenter

    Comment on: Claude Code: Now in Beta in ZedHacker News comment

    Estimates the free plan's 50 prompts a month at roughly US$8 of equivalent Claude API usage.

    Published Sep 4, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; counts toward Cost predictability and limits How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-04, free plan, needs a recheck
    Counts toward
    Cost predictability and limits, cost transparency: 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

  71. Mixed

    lemontheme, Hacker News commenter

    Comment on: Claude Code: Now in Beta in ZedHacker News comment

    Was blown away by Zed's agent as a first coding agent, moved to Claude Code weeks later, and canceled the 20 EUR per month subscription for AI features no longer used.

    Published Sep 4, 2025self-described: Developer describing their own use of Zed's AI features

    not counted, repeats a stronger account How GILD checked it
    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
    2025-09-04, needs a recheck
    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
    Still applicable

  72. Positive

    ppeetteerr, Hacker News commenter

    Comment on: Claude Code: Now in Beta in ZedHacker News comment

    Welcomes native Claude Code support but finds Cursor's autocomplete and predictions much more accurate than Zed's own model or Supermaven.

    Published Sep 3, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-03, needs a recheck
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  73. No opinion stated

    cedws, Hacker News commenter

    Comment on: Claude Code: Now in Beta in ZedHacker News comment

    Uses Zed and is moving towards containerising the dev environment, connecting Zed over SSH remote dev, because "all this agentic stuff seems like a security nightmare".

    Published Sep 3, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-03, needs a recheck
    Not counted
    no aspect: excluded, takes no position on any assessed aspect

    Checked Oct 30, 2026 under gild-policy/1.0.0. The scorecard

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  74. Positive

    dcre, Hacker News commenter

    Comment on: Claude Code: Now in Beta in ZedHacker News comment

    Reads ACP as Zed leaving agent logic to others, since prompting tricks are easy to copy and the next model generation absorbs them.

    Published Sep 3, 2025self-described: Developer describing their own use of Zed's AI features

    not counted, repeats a stronger account How GILD checked it
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-03, needs a recheck
    Not counted
    Adoption and upkeep, continuity: 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

  75. Negative

    kelthuzad, Hacker News commenter

    Comment on: Claude Code: Now in Beta in ZedHacker News comment

    Never had a problem with Cursor, while Zed panicked, crashed, and behaved inconsistently often.

    Published Sep 3, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-09-03, needs a recheck
    Counts toward
    Operational control, data control: unfavorable, G2 (2 units before bounds)
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  76. Mixed

    aexvir, GitHub issue author

    Support history with external ACP agentsGitHub issue

    Using Gemini via ACP in Zed v0.202.1 ("Zed Preview"), none of the threads created with the Gemini agent were saved to the history list of threads.

    Published Aug 28, 2025self-described: Using Gemini CLI through ACP on a pre-release Zed build

    Practitioner account, pseudonymous; direct use; counts toward Reliability How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-08-28, v0.202.1 (Zed Preview), needs a recheck
    Counts toward
    Reliability, run stability: unfavorable, G1 (1 unit before bounds), capped: C-relevance

    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
    Zed v0.202.1, Gemini CLI

  77. Positive

    trenchpilgrim, Hacker News commenter

    Comment on: Claude Opus 4.1Hacker News comment

    Uses ask mode to discuss approaches and draft patches, then write mode to implement and run tests and diagnostics, then a line-by-line review before a pull request.

    Published Aug 5, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-08-05, needs a recheck
    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
    Still applicable

  78. Negative

    gwking, Hacker News commenter

    Comment on: You can now disable all AI features in ZedHacker News comment

    Used Zed daily for over a month and went back to Cursor for the quality of its tab completion, which Zeta and Copilot did not match.

    Published Jul 23, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-07-23, Zeta, needs a recheck
    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
    Observed on
    Zeta edit predictions

  79. Negative

    kbdiaz, Hacker News commenter

    Comment on: You can now disable all AI features in ZedHacker News comment

    Calls Zed a great code editor but a weak AI editor: late to edit predictions, behind on agent UX, and without background agents like Cursor's.

    Published Jul 23, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Opinion; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-07-23, needs a recheck
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  80. Positive

    senko, Hacker News commenter

    Comment on: Coding with LLMs in the summer of 2025 (an update)Hacker News comment

    Runs each task in the agent panel: plans with Claude 4 Sonnet in thinking mode, then switches to Sonnet 4 in the same conversation to implement, then reviews and tests.

    Published Jul 21, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; counts toward Operational control How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-07-21, Claude 4 Sonnet, needs a recheck
    Counts toward
    Operational control, models and deployment: 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
    Observed on
    Claude 4 Sonnet and Gemini 2.5 Pro in the agent panel

  81. Positive

    José Valim, Chief Adoption Officer at Dashbit

    The path to Tidewave: beyond code intelligenceCompany blog post, Dashbit

    Valim credits Zed with an excellent job of bringing editor diagnostics and code actions into its agentic workflows, while most agent tools still see only the code as written.

    "The Zed editor also does an excellent job at integrating some editor features, such as diagnostics and code actions, into their agentic workflows."
    Excerpt, José Valim

    Published Jun 6, 2025Introducing Tidewave, Dashbit's runtime-aware tools for coding agents

    Practitioner account, name and role on an outside page; opinion; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Name and role on an outside page; Competitor staff: not counted as independent; Opinion; Needs recheck after 12 months
    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 (Chief Adoption Officer at Dashbit)
    Relationship
    vendor employee (self disclosed)
    How they know
    Opinion, no use stated
    Support
    No artifact or independent corroboration recorded
    Date and version
    2025-06-06, needs a recheck
    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

    Published on
    Engineering Blogs & Reviews
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Still applicable

  82. Mixed

    Victor Mota, co-founder of CoPlane

    Post on X by Victor MotaPost on X

    After a few days with Zed's new AI features, Mota found the Agent Panel pretty nice but short on polished defaults, and edit predictions never appeared. He still wants Zed as his default but flips back to Cursor when he hits an issue.

    "Despite all the quirks, I still find myself wanting to default to it, but then flipping back to Cursor when I run into an issue."
    Excerpt, Victor Mota

    Published May 10, 2025Trying Zed's new AI features against Cursor, including on his team's Python monorepo

    Practitioner account, pseudonymous; direct use; counts toward Adoption and upkeep How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; Competitor staff: not counted as independent; Used it directly; Specific details; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    former vendor employee (self disclosed)
    How they know
    Used it directly
    Support
    1 artifact (issue)
    Date and version
    2025-05-10, needs a recheck
    Counts toward
    Adoption and upkeep, setup: mixed, G2 (2 units before bounds)
    Not counted
    Delivered outcomes, context handling: 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, pending a recheck

    Published on
    Developer Communities
    Who
    Technical leadership
    Evidence
    Reported
    Applies to
    Needs a recheck
    Observed on
    Zed agent panel at launch

  83. Positive

    volkk, Hacker News commenter

    Comment on: Zed: High-performance AI Code EditorHacker News comment

    Rates the AI panel well below Cursor's but calls Zed one of the fastest programs on the machine; a later edit says the updated panel looks good.

    Published May 7, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, takes no position How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-05-07, needs a recheck
    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

  84. Mixed

    gyre007, Hacker News commenter

    Comment on: Zed: High-performance AI Code EditorHacker News comment

    Reports the agent edited files when asked only a question about the codebase, and asks for diffs that wait for approval.

    Published May 7, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-05-07, needs a recheck
    Not counted
    Operational control, execution control: 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
    Zed agent panel at launch

  85. Positive

    thestephen, Hacker News commenter

    Comment on: Zed: High-performance AI Code EditorHacker News comment

    Prefers Zed because the developer keeps control over API calls, where Cursor spent the API quota unexpectedly, and because Zed matches Sublime's speed.

    Published May 7, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-05-07, needs a recheck
    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
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable

  86. Positive

    DreaminDani, Hacker News commenter

    Comment on: Zed: High-performance AI Code EditorHacker News comment

    Finds the new agent panel does the right thing more often than Cursor or Windsurf. It gathers the right context, asks for feedback when needed, and has not looped between two failing fixes.

    Published May 7, 2025self-described: Developer describing their own use of Zed's AI features

    Practitioner account, pseudonymous; direct use; not counted, repeats a stronger account How GILD checked it
    Origin
    Published practitioner account
    Checked
    Pseudonymous; No tie to Zed found in GILD's check; Used it directly; Needs recheck after 12 months
    Role
    Pseudonymous account; identity not pursued
    Relationship
    No tie to Zed 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
    2025-05-07, needs a recheck
    Not counted
    Delivered outcomes, task completion: repeats a stronger account in its group
    Not counted
    Delivered outcomes, context handling: repeats a stronger account in its group
    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

    Published on
    Developer Communities
    Who
    Individual practitioner
    Evidence
    Reported
    Applies to
    Still applicable
    Observed on
    Zed agent panel at launch

Product documentation 9

Pages from Zed Industries, used to check facts for every group.

  1. Zed pricing

    Lists Personal at US$0 with your own keys or external agents, Pro at US$10 per month with unlimited edit predictions and US$5 of tokens, and Business at US$30 per seat per month. Hosted usage bills at API list price plus 10%.

    Checked Oct 25, 2026

  2. Zed for Business

    Describes org-wide controls over Zed-hosted models, edit predictions, and data sharing, with prompt sharing and training off by default; SSO, SAML, and SCIM are planned.

    Checked Oct 25, 2026

  3. Agent Panel

    Documents the panel for the Zed Agent and external agents, and states that history, checkpoints, and token usage display depend on each external agent's integration.

    Checked Oct 25, 2026

  4. External Agents

    Documents installing Claude, Codex, Gemini CLI, OpenCode, Copilot, Cursor, and other agents from the ACP Registry; each agent owns its own auth, billing, and data terms.

    Checked Oct 25, 2026

  5. Edit Prediction

    Documents Zeta, Zed's open model, as the default provider on Pro, trial, Student, and Business plans, with Copilot, Codestral, Mercury Coder, or a local model as alternatives.

    Checked Oct 25, 2026

  6. Parallel Agents

    Documents running several agent and terminal threads at once from the Threads Sidebar, with an agentic layout and a classic layout to restore.

    Checked Oct 25, 2026

  7. Tool Permissions

    Documents regex rules that allow, deny, or confirm agent tool calls such as terminal commands, file edits, and MCP tools.

    Checked Oct 25, 2026

  8. AI Privacy

    States Zed does not retain prompts or code context by default and that hosted model providers commit to no training and zero data retention, with stated exceptions.

    Checked Oct 25, 2026

  9. Zed is 1.0

    Announces Zed 1.0 on April 29, 2026 on Mac, Windows, and Linux, with parallel agents, edit predictions, ACP agents, and Zed for Business.

    Checked Oct 25, 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
SourceOriginal URLAuthor and contextWhoPublishedReview dateAppliesFindings
Post on X by Kang Cahya KerenID x-kangcahyakeren | Developer Communitiesx.com/kangcahyakeren/status/2111135076407025792Kang Cahya Keren, developer and bloggerself-described: Moved to Zed from VS Code and AntigravityIndividual practitionerPublished Oct 16, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Nenad NovakovicID x-nnx0r | Developer Communitiesx.com/nnx0r/status/2108511053214560622Nenad Novakovic, founderself-described: Founder building his own appsTechnical leadershipPublished Oct 9, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Jacob WolfID x-JacobWolf | Developer Communitiesx.com/JacobWolf/status/2107770883762950196Jacob Wolf, leads podcasts and integrations engineering at beehiivself-described: Engineering lead switching between OpenCode, Cursor, and Claude CodeTechnical leadershipPublished Oct 7, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Eluert MukjaID x-mukja_e | Developer Communitiesx.com/mukja_e/status/2106808525825470604Eluert Mukja, full-stack developerself-described: Built a phone companion for Zed's agent panelIndividual practitionerPublished Oct 4, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed and devcontainersID lead3-hn-49941993 | Developer Communitiesnews.ycombinator.com/item?id=49941993jackjeff, developer using Zed with devcontainersself-described: Zed and devcontainers for a development environmentIndividual practitionerPublished Oct 3, 2026Assessment reviewed Nov 1, 2026Still applicableListed, no finding position
Post on X by rodesiaID x-rodesia | Developer Communitiesx.com/rodesia/status/2106049530382991870rodesia, solo builder of a web platformself-described: Building and running a web platform aloneIndividual practitionerPublished Oct 2, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Chris ReynoldsID x-AdjustedTwit | Developer Communitiesx.com/AdjustedTwit/status/2103431245673750875Chris Reynolds, IT Directorself-described: IT director using Zed and Sublime as minimal editorsTechnical leadershipPublished Sep 25, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by ArisID x-riipandi | Developer Communitiesx.com/riipandi/status/2103590820553294064Aris (riipandi), developer on Xself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 25, 2026Assessment reviewed Nov 1, 2026Still applicable
Vibe Coding Developer Productivity ToolsID l3b-04 | Engineering Blogs & Reviewsmikemcquaid.com/vibe-coding-developer-productivity-tools/Mike McQuaid, CTPO at AdministrateBuilt AgentIDE for his own agent workflow; coworkers at Administrate and Homebrew maintainers use itTechnical leadershipPublished Sep 24, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Zed collaborative agent workflowID lead3-hn-49756071 | Developer Communitiesnews.ycombinator.com/item?id=49756071emerongi, engineer reviewing Zed's collaborative agent workflowself-described: Response to a video of Zed collaborative reviewIndividual practitionerPublished Sep 18, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Andrey TarantsovID x-andreyvit | Developer Communitiesx.com/andreyvit/status/2100851571856711738Andrey Tarantsov, Technical director at Bubblehouseself-described: Technical director trying Codex and Grok Build as external agentsTechnical leadershipPublished Sep 18, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed prompt overheadID lead3-hn-49740752 | Developer Communitiesnews.ycombinator.com/item?id=49740752NortySpock, developer evaluating Zed's default promptself-described: Zed editor prompt overheadIndividual practitionerPublished Sep 17, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: trying Zed againID lead3-hn-49488570 | Developer Communitiesnews.ycombinator.com/item?id=49488570jackjeff, developer evaluating Zed's agent workflowself-described: Retesting Zed after an earlier trialIndividual practitionerPublished Aug 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Cannot resume/open an existing Claude Code session in Zed when it is running as a background agent (works in VS Code)ID gh-62488 | Developer Communitiesgithub.com/zed-industries/zed/issues/62488faisal-fida, GitHub issue authorself-described: Claude Code over SSH remote developmentIndividual practitionerPublished Aug 11, 2026Assessment reviewed Nov 1, 2026Still applicable
External agents are unavailable in shared projects while in CollaborationID gh-61343 | Developer Communitiesgithub.com/zed-industries/zed/issues/61343xbt573, GitHub issue authorself-described: Using a shared project in a Zed collaboration channelIndividual practitionerPublished Jul 20, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Peter ThomsonID l3b-01 | Developer Communitiesx.com/PeterJThomson/status/2068875061583569346Peter Thomson, CTO at Icehouse VenturesIcehouse Ventures engineering team, which keeps full-agent tools as daily driversTechnical leadershipPublished Jun 22, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Software is made between commitsID hn-48493794 | Developer Communitiesnews.ycombinator.com/item?id=48493794slopinthebag, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Jun 11, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by arcID x-arcbjorn | Developer Communitiesx.com/arcbjorn/status/2060548170455646376arc (arcbjorn), agent systems and ML engineerself-described: Zed user since the 2022 private betaIndividual practitionerPublished May 30, 2026Assessment reviewed Nov 1, 2026Still applicable
Claude Code ACP session enters unrecoverable state after hitting usage limitID gh-55501 | Developer Communitiesgithub.com/zed-industries/zed/issues/55501jordandakota, GitHub issue authorself-described: Claude Code over ACP on a Claude plan with usage limitsIndividual practitionerPublished May 2, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47959294 | Developer Communitiesnews.ycombinator.com/item?id=47959294zephod, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 30, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47960850 | Developer Communitiesnews.ycombinator.com/item?id=47960850presentation, Hacker News commenterself-described: Developer whose company pays for CursorIndividual practitionerPublished Apr 30, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47963728 | Developer Communitiesnews.ycombinator.com/item?id=47963728matthewtse, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 30, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47949179 | Developer Communitiesnews.ycombinator.com/item?id=47949179recov, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47949277 | Developer Communitiesnews.ycombinator.com/item?id=47949277sodacanner, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47949397 | Developer Communitiesnews.ycombinator.com/item?id=47949397NortySpock, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47949416 | Developer Communitiesnews.ycombinator.com/item?id=47949416JnnydevDude, Hacker News commenterself-described: Light Zed user for a few monthsIndividual practitionerPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47949857 | Developer Communitiesnews.ycombinator.com/item?id=47949857jeppester, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47951774 | Developer Communitiesnews.ycombinator.com/item?id=47951774mlsu, Hacker News commenterself-described: Developer new to Zed on a mixed C and Rust projectIndividual practitionerPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47952904 | Developer Communitiesnews.ycombinator.com/item?id=47952904scottmessinger, Hacker News commenterself-described: Zed user for yearsIndividual practitionerPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed 1.0ID hn-47954273 | Developer Communitiesnews.ycombinator.com/item?id=47954273ksajadi, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Omar McAdamID l3b-02 | Developer Communitiesx.com/OmarMcAdam/status/2049563568539140467Omar McAdam, CTO at Different AICTO of Different AI, which builds OpenWork, with OpenCode as his coding agentTechnical leadershipPublished Apr 29, 2026Assessment reviewed Nov 1, 2026Current
Post on X by 0xSeroID x-0xSero | Developer Communitiesx.com/0xSero/status/20485253485857673940xSero, developer on Xself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 26, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Parallel agents in ZedID hn-47876720 | Developer Communitiesnews.ycombinator.com/item?id=47876720tankmohit11, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 23, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Parallel agents in ZedID hn-47867353 | Developer Communitiesnews.ycombinator.com/item?id=47867353jamie_ca, Hacker News commenterself-described: Developer whose employer provides GitHub CopilotIndividual practitionerPublished Apr 22, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Parallel agents in ZedID hn-47867370 | Developer Communitiesnews.ycombinator.com/item?id=47867370verse, Hacker News commenterself-described: Daily Zed userIndividual practitionerPublished Apr 22, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Parallel agents in ZedID hn-47867852 | Developer Communitiesnews.ycombinator.com/item?id=47867852lfx, Hacker News commenterself-described: Zed user for over a yearIndividual practitionerPublished Apr 22, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Parallel agents in ZedID hn-47870027 | Developer Communitiesnews.ycombinator.com/item?id=47870027conqrr, Hacker News commenterself-described: Developer using Zed at home and Claude Code at workIndividual practitionerPublished Apr 22, 2026Assessment reviewed Nov 1, 2026Still applicable
Sandboxes and Worktrees: My secure Agentic AI SetupID l3b-03 | Engineering Blogs & Reviewsmikemcquaid.com/sandboxed-agent-worktrees-my-coding-and-ai-setup-in-2026/Mike McQuaid, CTPO at AdministrateRuns sandboxed Codex and Claude Code agents on Homebrew and Administrate repositoriesTechnical leadershipPublished Apr 14, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Reallocating $100/Month Claude Code Spend to Zed and OpenRouterID hn-47701606 | Developer Communitiesnews.ycombinator.com/item?id=47701606kisamoto (Ewan), author of the Braw.dev post under discussionself-described: Developer moving a US$100 per month Claude Code budget to Zed and OpenRouterIndividual practitionerPublished Apr 9, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Reallocating $100/Month Claude Code Spend to Zed and OpenRouterID hn-47701796 | Developer Communitiesnews.ycombinator.com/item?id=47701796philipp-gayret, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 9, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: Reallocating $100/Month Claude Code Spend to Zed and OpenRouterID hn-47710450 | Developer Communitiesnews.ycombinator.com/item?id=47710450avilay, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Apr 9, 2026Assessment reviewed Nov 1, 2026Still applicable
Reallocating $100/Month Claude Code spend to Zed and OpenRouterID blog-braw | Developer Communitiesbraw.dev/blog/2026-04-06-reallocating-100-month-claude-spend/Ewan (kisamoto on Hacker News), author of Braw.devself-described: Developer moving a US$100 per month Claude Code budget to Zed and OpenRouterIndividual practitionerPublished Apr 6, 2026Assessment reviewed Nov 1, 2026Still applicable
All agent actions extremely slowID gh-53102 | Developer Communitiesgithub.com/zed-industries/zed/issues/53102secondl1ght, GitHub issue authorself-described: Zed Agent on LinuxIndividual practitionerPublished Apr 3, 2026Assessment reviewed Nov 1, 2026Still applicable
Claude Code ACP increases zed energy consumption 100xID gh-51597 | Developer Communitiesgithub.com/zed-industries/zed/issues/51597princhman, GitHub issue authorself-described: Running the Claude agent over ACP on macOSIndividual practitionerPublished Mar 15, 2026Assessment reviewed Nov 1, 2026Still applicable
GPT-5.3 Codex from copilot provider is unusable in zedID gh-50559 | Developer Communitiesgithub.com/zed-industries/zed/issues/50559somtooo, GitHub issue authorself-described: Using GPT-5.3 Codex from a GitHub Copilot subscription in the Zed AgentIndividual practitionerPublished Mar 3, 2026Assessment reviewed Nov 1, 2026Needs a recheck
Post on X by Quinn SlackID l3b-10 | Developer Communitiesx.com/sqs/status/2022664183012266291Quinn Slack, CEO and Member of Technical Staff at AmpRuns Amp as his coding agent and Zed as his editorTechnical leadershipPublished Feb 14, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Zed editor switching graphics lib from blade to wgpuID hn-47009503 | Developer Communitiesnews.ycombinator.com/item?id=47009503trcf23, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Feb 13, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Quinn SlackID l3b-08 | Developer Communitiesx.com/sqs/status/2021147835400601959Quinn Slack, CEO and Member of Technical Staff at AmpMoving Amp's own codebase toward feedback loops that coding agents useTechnical leadershipPublished Feb 10, 2026Assessment reviewed Nov 1, 2026Current
Post on X by Stephen HaneyID l3b-06 | Developer Communitiesx.com/stephenhaney/status/2016592739018977339Stephen Haney, founder of PaperFounder of Paper, a design tool companyTechnical leadershipPublished Jan 28, 2026Assessment reviewed Nov 1, 2026Current
Comment on: I switched from VSCode to ZedID hn-46508638 | Developer Communitiesnews.ycombinator.com/item?id=46508638Abishek_Muthian, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Jan 6, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: I switched from VSCode to ZedID hn-46499235 | Developer Communitiesnews.ycombinator.com/item?id=46499235RamblingCTO, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Jan 5, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: I switched from VSCode to ZedID hn-46499411 | Developer Communitiesnews.ycombinator.com/item?id=46499411giancarlostoro, Hacker News commenterself-described: Developer leaving a JetBrains subscription after nearly 10 yearsIndividual practitionerPublished Jan 5, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: I switched from VSCode to ZedID hn-46499805 | Developer Communitiesnews.ycombinator.com/item?id=46499805dmix, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Jan 5, 2026Assessment reviewed Nov 1, 2026Still applicable
Comment on: I switched from VSCode to ZedID hn-46499874 | Developer Communitiesnews.ycombinator.com/item?id=46499874Octoth0rpe, Hacker News commenterself-described: Early Zed adopterIndividual practitionerPublished Jan 5, 2026Assessment reviewed Nov 1, 2026Still applicable
I switched from VSCode to ZedID blog-tenthousandmeters | Developer Communitiestenthousandmeters.com/blog/i-switched-from-vscode-to-zed/Victor Skvortsov, author of Ten thousand metersself-described: Python and Go developer who uses a CLI agent (Codex) for AI workIndividual practitionerPublished Jan 3, 2026Assessment reviewed Nov 1, 2026Still applicable
Post on X by Dhravya ShahID l3b-07 | Developer Communitiesx.com/DhravyaShah/status/2007562825041068050Dhravya Shah, founder of SupermemoryFounder of Supermemory, a memory layer for AI appsTechnical leadershipPublished Jan 3, 2026Assessment reviewed Nov 1, 2026Current
Comment on: Zed is our officeID hn-45918549 | Developer Communitiesnews.ycombinator.com/item?id=45918549travisgriggs, Hacker News commenter at a 2-3 person shopself-described: A 2-3 person shop working across four operating systems and 5+ languagesVery small teamPublished Nov 13, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Codex Is Live in ZedID hn-45627687 | Developer Communitiesnews.ycombinator.com/item?id=45627687lukaslalinsky, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Oct 18, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Codex Is Live in ZedID hn-45615797 | Developer Communitiesnews.ycombinator.com/item?id=45615797mcjiggerlog, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Oct 17, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Codex Is Live in ZedID hn-45608280 | Developer Communitiesnews.ycombinator.com/item?id=45608280mosselman, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Oct 16, 2025Assessment reviewed Nov 1, 2026Still applicable
A new direction for AI developer tooling featuring José Valim, creator of Tidewave (Changelog & Friends #112)ID l3b-05 | Talks & Podcastschangelog.com/friends/112José Valim, Chief Adoption Officer at DashbitCreator of Elixir, building Dashbit's Tidewave coding agent on ACPTechnical leadershipPublished Oct 10, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedID hn-45362991 | Developer Communitiesnews.ycombinator.com/item?id=45362991agrippanux, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 24, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedID hn-45363169 | Developer Communitiesnews.ycombinator.com/item?id=45363169genshii, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 24, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedID hn-45363377 | Developer Communitiesnews.ycombinator.com/item?id=45363377WD-42, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 24, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedID hn-45363726 | Developer Communitiesnews.ycombinator.com/item?id=45363726oakesm9, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 24, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedID hn-45363953 | Developer Communitiesnews.ycombinator.com/item?id=45363953pkilgore, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 24, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedID hn-45364039 | Developer Communitiesnews.ycombinator.com/item?id=45364039sethhochberg, Hacker News commenter buying AI tools for an organizationself-described: Corporate purchaser governing employee AI access through a company-managed OpenAI tenantTechnical leadershipPublished Sep 24, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed's Pricing Has Changed: LLM Usage Is Now Token-BasedID hn-45365482 | Developer Communitiesnews.ycombinator.com/item?id=45365482hakanensari, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 24, 2025Assessment reviewed Nov 1, 2026Still applicable
Zed + Claude Code: A Beautiful Promise That's Not Quite There YetID blog-dobrohotov | Developer Communitiesalekdobrohotov.substack.com/p/zed-claude-code-a-beautiful-promiseAlek Dobrohotov, Product Manager at C&Cself-described: Builds internal tools for retail, education, and B2B teams at C&C, an Apple Premium PartnerProfessional teamPublished Sep 6, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Claude Code: Now in Beta in ZedID hn-45122771 | Developer Communitiesnews.ycombinator.com/item?id=45122771chillfox, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 4, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Claude Code: Now in Beta in ZedID hn-45124242 | Developer Communitiesnews.ycombinator.com/item?id=45124242lemontheme, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 4, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Claude Code: Now in Beta in ZedID hn-45118464 | Developer Communitiesnews.ycombinator.com/item?id=45118464ppeetteerr, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 3, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Claude Code: Now in Beta in ZedID hn-45118467 | Developer Communitiesnews.ycombinator.com/item?id=45118467cedws, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 3, 2025Assessment reviewed Nov 1, 2026Still applicableListed, no finding position
Comment on: Claude Code: Now in Beta in ZedID hn-45119934 | Developer Communitiesnews.ycombinator.com/item?id=45119934dcre, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 3, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Claude Code: Now in Beta in ZedID hn-45120139 | Developer Communitiesnews.ycombinator.com/item?id=45120139kelthuzad, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Sep 3, 2025Assessment reviewed Nov 1, 2026Still applicable
Support history with external ACP agentsID gh-37074 | Developer Communitiesgithub.com/zed-industries/zed/issues/37074aexvir, GitHub issue authorself-described: Using Gemini CLI through ACP on a pre-release Zed buildIndividual practitionerPublished Aug 28, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Claude Opus 4.1ID hn-44805827 | Developer Communitiesnews.ycombinator.com/item?id=44805827trenchpilgrim, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Aug 5, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: You can now disable all AI features in ZedID hn-44661637 | Developer Communitiesnews.ycombinator.com/item?id=44661637gwking, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Jul 23, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: You can now disable all AI features in ZedID hn-44661758 | Developer Communitiesnews.ycombinator.com/item?id=44661758kbdiaz, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Jul 23, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Coding with LLMs in the summer of 2025 (an update)ID hn-44632623 | Developer Communitiesnews.ycombinator.com/item?id=44632623senko, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished Jul 21, 2025Assessment reviewed Nov 1, 2026Still applicable
The path to Tidewave: beyond code intelligenceID l3b-11 | Engineering Blogs & Reviewsdashbit.co/blog/the-path-to-tidewaveJosé Valim, Chief Adoption Officer at DashbitIntroducing Tidewave, Dashbit's runtime-aware tools for coding agentsTechnical leadershipPublished Jun 6, 2025Assessment reviewed Nov 1, 2026Still applicable
Post on X by Victor MotaID l3b-09 | Developer Communitiesx.com/vimota/status/1921270079054049476Victor Mota, co-founder of CoPlaneTrying Zed's new AI features against Cursor, including on his team's Python monorepoTechnical leadershipPublished May 10, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Zed: High-performance AI Code EditorID hn-43915163 | Developer Communitiesnews.ycombinator.com/item?id=43915163volkk, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished May 7, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed: High-performance AI Code EditorID hn-43916244 | Developer Communitiesnews.ycombinator.com/item?id=43916244gyre007, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished May 7, 2025Assessment reviewed Nov 1, 2026Needs a recheck
Comment on: Zed: High-performance AI Code EditorID hn-43917489 | Developer Communitiesnews.ycombinator.com/item?id=43917489thestephen, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished May 7, 2025Assessment reviewed Nov 1, 2026Still applicable
Comment on: Zed: High-performance AI Code EditorID hn-43921223 | Developer Communitiesnews.ycombinator.com/item?id=43921223DreaminDani, Hacker News commenterself-described: Developer describing their own use of Zed's AI featuresIndividual practitionerPublished May 7, 2025Assessment reviewed Nov 1, 2026Still applicable
Zed pricingID pd-01 | Product Documentationzed.dev/pricingZed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only
Zed for BusinessID pd-02 | Product Documentationzed.dev/businessZed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only
Agent PanelID pd-03 | Product Documentationzed.dev/docs/ai/agent-panelZed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only
External AgentsID pd-04 | Product Documentationzed.dev/docs/ai/external-agentsZed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only
Edit PredictionID pd-05 | Product Documentationzed.dev/docs/ai/edit-predictionZed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only
Parallel AgentsID pd-06 | Product Documentationzed.dev/docs/ai/parallel-agentsZed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only
Tool PermissionsID pd-07 | Product Documentationzed.dev/docs/ai/tool-permissionsZed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only
AI PrivacyID pd-08 | Product Documentationzed.dev/docs/ai/privacy-and-securityZed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only
Zed is 1.0ID pd-09 | Product Documentationzed.dev/blog/zed-1-0Zed IndustriesOfficialNot counted (documentation)No date statedDocumentation checked Oct 25, 2026CurrentVerification only