Every source behind the read

39 sources in Engineering leaders and teams, with product documentation Showing all 68 sources

1. Positive

   Jim Freeman, founder at Punt Labs

   ci(review): pilot Qodo-first review with bounded rounds (vox-2q95)GitHub pull request on punt-labs/vox

   Across 923 pull requests, Punt Labs hand-classified 50 comments per bot. Of Qodo's, 20% were real bugs and 54% were nits, with 12% false positives, and Qodo caused the fewest extra pushes. The team turned Copilot review off and made Qodo the first reviewer, running once on open with only high-severity findings posted inline.

   "Copilot is the noise source; Bugbot finds the most real bugs; Qodo converges but its false positives were all process "Rule violations"."

   Published Oct 23, 2026Punt Labs, open source tools for agentic software engineering teams, with AI agents opening most pull requests

   Counts toward

   • Overall signal
   • Real bug catches: Positive
   • Configurable review rules: Positive
   • Comment noise and wrong findings: Raised as a concern
   • Does Qodo's reviewer earn a permanent place on the pull request?: Kept it
   • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer Qodo

   Published on

   Developer communities

   Who

   Technical leadership

   Evidence

   Measured

   Applies to

   Current

   Observed on

   Qodo v2 next to Copilot and Cursor Bugbot, measured on 923 pull requests from 2026

2. Positive

   Titus Fortner, Technical Leadership Committee member at Selenium

   [build] automatically generate Qodo reviews from PRs by committersGitHub pull request on SeleniumHQ/selenium

   Because Qodo pauses reviews for authors without a seat, most Selenium pull requests went unreviewed unless someone with a seat asked. The project now posts the Qodo commands from a CI account that holds a seat, so every committer pull request gets a description and a review on open and on each push.

   "Qodo pauses reviews for PR authors without a Qodo seat, so most PRs only get reviewed when someone with a seat comments…"

   Published Oct 12, 2026Selenium browser automation project, multi-language monorepo with a committers team and outside contributors

   Counts toward

   • Overall signal
   • Credits, trials, and price: Discussed without concern
   • Does Qodo's reviewer earn a permanent place on the pull request?: Kept it

   Published on

   Developer communities

   Who

   Technical leadership

   Evidence

   Reported

   Applies to

   Current

   Observed on

   Qodo agentic describe and review, triggered by the selenium-ci account

3. Mixed

   myakove, mtv-api-tests collaborator

   Docs policy: generated site output is committed, not hand-edited - Qodo rule 1255924 conflicts with .pr_agent.toml ignore globGitHub issue

   Red Hat QE reports a high-severity Qodo violation on every documentation PR. The rule flags committed generated files that .pr_agent.toml already excludes from review.

   Published Oct 8, 2026self-described: Red Hat QE, Migration Toolkit for Virtualization API test suite

   Counts toward

   • Overall signal
   • Configurable review rules: Mixed or negative
   • Comment noise and wrong findings: Raised as a concern

   Published on

   Developer communities

   Who

   Professional team

   Evidence

   Reported

   Applies to

   Current

4. Mixed

   Chris Vancoillie (eleshar), LightSpeed WordPress Development

   task: qodo-pr-agent - Validate pilot credential boundary and activationGitHub issue

   LightSpeed caps its self-hosted PR-Agent model key at US$20 a month, about 140 automatic runs by its estimate. The release pins an older LiteLLM model map, which prevents a move to Sonnet 5.5.

   Published Sep 24, 2026self-described: LightSpeed (lightspeedwp), an organization-wide pilot of self-hosted PR-Agent with an Anthropic key capped at US$20 a month

   Counts toward

   • Overall signal
   • Credits, trials, and price: Discussed without concern
   • Missing reviews and setup: Raised as a concern
   • Security and data exposure: Discussed without concern
   • Self-hosting on your own model keys matters

   Published on

   Developer communities

   Who

   Professional team

   Evidence

   Reported

   Applies to

   Current

   Observed on

   PR-Agent v0.46.0 Docker image with Claude Sonnet 5

5. Mixed

   Rahul S., reviewer on G2

   Great Cross-Repo PR Insights, Though Severity Flags Can Miss the MarkG2 review, syndicated on AWS Marketplace

   Rahul S. rates Qodo 3 of 5. Their team uses it as an extra check on every pull request and values its cross-repository context. It sometimes flags trivial issues at high severity.

   Published Sep 24, 2026self-described: Team runs Qodo on all pull requests in its AI development lifecycle

   Counts toward

   • Overall signal
   • Comment noise and wrong findings: Raised as a concern
   • A first pass, with humans owning the merge

   Published on

   Engineering blogs and reviews

   Who

   Professional team

   Evidence

   Reported

   Applies to

   Current

6. Mixed

   cptkoolbeenz, DAQiFi firmware team member

   review config: Qodo Rule 232249 contradicts CLAUDE.md's atomicity rule (and its own cited precedent #1028)GitHub issue

   A Qodo rule contradicts the project's documented atomicity rule and will fire on every related PR. The team declined one valid lock-free fix because of cost.

   Published Sep 18, 2026self-described: DAQiFi Nyquist firmware (FreeRTOS on PIC32)

   Counts toward

   • Overall signal
   • Suggested fixes: Positive
   • Configurable review rules: Mixed or negative
   • Comment noise and wrong findings: Raised as a concern

   Published on

   Developer communities

   Who

   Professional team

   Evidence

   Reported

   Applies to

   Current

7. Negative

   oscarestudillom, Hacker News commenter

   Comment on: GPT-6 Astra in code review: Gains, privacy, and costHacker News comment

   oscarestudillom's team found CodeRabbit and Qodo unusable because of noise. Two engineers built an internal reviewer instead.

   Published Sep 9, 2026self-described: Team that added AI review because senior engineers kept repeating the same comments

   Not counted

   Its author co-built Revix AI, a competing review tool, and the post criticises Qodo. Kept in the record; it takes part in no figure.

   Published on

   Developer communities

   Who

   Professional team

   Evidence

   Reported

   Applies to

   Current

8. Positive

   Vivaan K., reviewer on G2

   Big-Picture Code Reviews with Qodo, Great for Catching Logic and Dependency IssuesG2 review, syndicated on AWS Marketplace

   Vivaan K. rates Qodo 4 of 5. The data engineer values repository-wide checks for logic and dependency issues before merge. Judging findings still requires pipeline and business knowledge.

   Published Aug 25, 2026self-described: Data engineer reviewing pipeline changes against team coding standards

   Counts toward

   • Overall signal
   • Real bug catches: Positive
   • Comment noise and wrong findings: Discussed without concern

   Published on

   Engineering blogs and reviews

   Who

   Professional team

   Evidence

   Reported

   Applies to

   Current

9. Positive

   Subhramit Basu Bhowmick, maintainer at JabRef

   Add Qodo acknowledgement actionGitHub pull request on JabRef/jabref

   JabRef maintainers say Qodo has caught things they would otherwise have overlooked, and they kept having to remind authors to read its comments. They added a check that fails until the author replies to each Qodo comment or a push makes it outdated.

   "Over time, Qodo has proved to be useful in catching things that would've otherwise been overlooked."

   Published Jul 26, 2026JabRef open source reference manager, a Java desktop app with a large share of AI-assisted outside pull requests

   Counts toward

   • Overall signal
   • Real bug catches: Positive
   • A first pass, with humans owning the merge
   • Does Qodo's reviewer earn a permanent place on the pull request?: Kept it

   Published on

   Developer communities

   Who

   Professional team

   Evidence

   Reported

   Applies to

   Current

   Observed on

   Qodo free plan for open source projects on JabRef pull requests

10. Negative

    Mark H., reviewer on G2

    Underwhelming Experience with Limited Features for the PriceG2 review, syndicated on AWS Marketplace

    Mark H. rates Qodo 1 of 5 and prefers Greptile after four months without visible product progress. They cite weak analytics, unintuitive generated rules, missing repository context, and broken GitHub sign-up.

    Published Jun 13, 2026self-described: Team members joined through GitHub; context features unavailable

    Counts toward

    • Overall signal
    • Configurable review rules: Mixed or negative
    • Missing reviews and setup: Raised as a concern
    • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer another

    Published on

    Engineering blogs and reviews

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Current

11. Negative

    lukeasrodgers, Hacker News commenter

    Comment on: Open Code Review - An AI-powered code review CLI toolHacker News comment

    lukeasrodgers' team tried CodeRabbit and Qodo. They found both far worse than a thin in-house wrapper around Claude and Codex with per-repository skills.

    Published Jun 5, 2026self-described: Employer team

    Counts toward

    • Overall signal
    • Does Qodo's reviewer earn a permanent place on the pull request?: Dropped it
    • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer another

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Current

12. Positive

    Mohit Kumar, maintainer of cross-cluster-replication at OpenSearch

    [Enhancement] Enable AI-powered PR code review and suggestions (PR-Agent via opensearch-build)GitHub issue on opensearch-project/cross-cluster-replication

    A maintainer asked to bring the OpenSearch project's PR-Agent reviewer on Amazon Bedrock to cross-cluster-replication, saying that on the main OpenSearch repository it catches null pointer risks, wrong allocation IDs, missing error handling, and design problems before human review. The project onboarded the workflow to the repository.

    "…it catches issues like null pointer risks, incorrect allocation ID usage, missing error handling, and architectural concerns before human reviewers even look at the PR…"

    Published May 7, 2026OpenSearch project repositories maintained by Amazon engineers, sharing reusable review workflows from opensearch-build

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • Self-hosting on your own model keys matters
    • Does Qodo's reviewer earn a permanent place on the pull request?: Kept it

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Current

    Observed on

    Self-hosted Code-Diff-Reviewer workflow on open source Qodo PR-Agent with Amazon Bedrock models

13. Mixed

    Veli Karakaya, Bilkent University, with Baykal Mehmet Uçar of Beko

    Understanding the Limits of Automated Evaluation for Code Review Bots in PracticeResearch paper, arXiv (EASE 2026)

    Of 2,604 labeled comments from the reviewer Beko built on open source PR-Agent and ran on GPT-4 Turbo, engineers marked 1,733 (about 66%) fixed and 871 (about 34%) wontFix. Beko's director of software engineering says those labels reflect delivery pressure as well as comment quality, so the bots need continuous monitoring.

    "We analyze an industrial dataset from Beko comprising 2,604 bot-generated PR comments, each labeled by software engineers as fixed/wontFix."

    Published Apr 27, 2026self-described: Beko's production pull request workflow on Azure DevOps, where developers must label every bot comment before merge

    Counts toward, pending a recheck

    • Overall signal
    • Comment noise and wrong findings: Discussed without concern

    Published on

    Engineering blogs and reviews

    Who

    Organization-wide

    Evidence

    Measured

    Applies to

    Needs a recheck

    Observed on

    Code review agent built on open source Qodo PR-Agent, on GPT-4 Turbo

14. Positive

    Ambrish Vadnerkar, Medium

    How I Added AI Code Reviews to Our GitLab Pipeline Using PR-AgentPersonal blog post, Medium

    Ambrish Vadnerkar found generated descriptions the biggest benefit after a few months of PR-Agent on every merge request. It caught a hardcoded API key, but noise persisted. Vadnerkar worries that the team will rely on it too much.

    Published Apr 6, 2026self-described: Their team's GitLab project, PR-Agent as an advisory CI job on every merge request with OpenAI, then Gemini 2.5 Flash

    Counts toward

    • Overall signal
    • PR summaries and effort labels: Positive
    • Real bug catches: Positive
    • Configurable review rules: Positive
    • Comment noise and wrong findings: Raised as a concern
    • Credits, trials, and price: Discussed without concern
    • Security and data exposure: Discussed without concern
    • A first pass, with humans owning the merge
    • Self-hosting on your own model keys matters

    Published on

    Engineering blogs and reviews

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Current

    Observed on

    PR-Agent in GitLab CI, codiumai/pr-agent:latest

15. Negative

    mattvv, Hacker News commenter

    Comment on: A real-world benchmark for AI code reviewHacker News comment

    mattvv ruled Qodo out at US$30 per developer a month with 20 pull requests per user. Some developers on their team open that many in a day.

    Published Feb 4, 2026self-described: Team whose developers open many pull requests a day

    Counts toward

    • Overall signal
    • Value for Money: Mixed or negative
    • Credits, trials, and price: Raised as a concern

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Current

    Observed on

    Qodo pricing in February 2026: US$30 per developer per month, 20 pull requests per user per month

16. Negative

    swishfishdemolish, Indie Hackers member

    We Ran 11 AI PR Bots (and kept 1)Indie Hackers post

    The Indie Hackers member ranked Qodo eighth among 11 review bots tested on a production repository. It hallucinated often and lacked settings to cut the noise, though it was relatively cheap.

    Published Jan 29, 2026self-described: Team that ran 11 review bots on a production repository and kept Cursor Bugbot

    Counts toward

    • Overall signal
    • Configurable review rules: Mixed or negative
    • Comment noise and wrong findings: Raised as a concern
    • Credits, trials, and price: Discussed without concern
    • Does Qodo's reviewer earn a permanent place on the pull request?: Dropped it
    • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer another

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Measured

    Applies to

    Current

17. Mixed

    dbudwin, PR-Agent user

    Is it possible to remember code suggestions from the previous push?GitHub issue

    dbudwin's PR-Agent setup repeated suggestions on every push. Maintainers later added a persistent inline comments setting to skip suggestions already posted.

    Published Jan 27, 2026self-described: Team running open source PR-Agent in GitHub Actions on every push, with Claude Sonnet 4.5 on Amazon Bedrock

    Counts toward

    • Overall signal
    • Configurable review rules: Positive
    • Comment noise and wrong findings: Raised as a concern
    • Self-hosting on your own model keys matters

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Current

    Observed on

    PR-Agent GitHub Action with Claude Sonnet 4.5 on Bedrock

18. Positive

    outofdistro, Hacker News commenter

    Comment on: Graphite is joining CursorHacker News comment

    outofdistro's team has used Qodo for a while. It occasionally finds a serious issue, but effort labels and file-by-file walkthroughs help most by speeding human review.

    Published Dec 20, 2025self-described: Employer team

    Counts toward

    • Overall signal
    • PR summaries and effort labels: Positive
    • Real bug catches: Positive
    • A first pass, with humans owning the merge
    • Does Qodo's reviewer earn a permanent place on the pull request?: Kept it

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Still applicable

19. Mixed

    archon810, Hacker News commenter

    Comment on: Graphite is joining CursorHacker News comment

    archon810 runs Qodo beside Gemini, Cursor Bugbot, and Sentry on pull requests. They usually prefer Gemini, though the others sometimes catch bugs it misses.

    Published Dec 19, 2025self-described: Employer repositories, several AI reviewers at once

    Counts toward

    • Overall signal
    • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer another

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Still applicable

20. Negative

    lukhnos, OpenVanilla collaborator

    Remove Qodo's PR agent CI workflow configGitHub pull request

    lukhnos removed Qodo's PR agent workflow after a failed attempt to revive it. Its last review was in April, and Gemini and Copilot had taken over.

    Published Dec 10, 2025self-described: OpenVanilla fcitx5-mcbopomofo input method project

    Counts toward, pending a recheck

    • Overall signal
    • Dashboard and setup friction: Raised as a concern
    • Missing reviews and setup: Raised as a concern
    • Does Qodo's reviewer earn a permanent place on the pull request?: Dropped it
    • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer another

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Needs a recheck

21. Mixed

    spanwair, PR-Agent user

    Incorrect Inline Code Suggestion Formatting in Azure DevOpsGitHub issue

    spanwair cannot apply PR-Agent's Azure DevOps suggestions even after heavy tuning. Suggestions arrive on one line, duplicated, or malformed. Other users report the same.

    Published Nov 20, 2025self-described: PR-Agent in an Azure DevOps pipeline

    Counts toward

    • Overall signal
    • Suggested fixes: Mixed or negative
    • Git platform coverage: Mixed or negative

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Still applicable

    Observed on

    codiumai/pr-agent:latest on Azure DevOps

22. Positive

    Jonah V., reviewer on G2

    Effortless Communication for Dev TeamsG2 review, syndicated on AWS Marketplace

    Jonah V. rates Qodo 4.5 of 5. It reduced the time and friction their team spent on code review.

    Published Nov 14, 2025self-described: Development team that found code review a time sink

    Counts toward

    • Overall signal
    • A first pass, with humans owning the merge

    Published on

    Engineering blogs and reviews

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Still applicable

23. Mixed

    Umut Cihan, Bilkent University, with co-authors from Beko

    Automated Code Review In PracticeConference talk page, ICSE 2025 Software Engineering in Practice track

    At Beko, developers resolved 73.8% of the comments from a reviewer built on open source Qodo PR-Agent. Average pull request closure time rose from 5 hours 52 minutes to 8 hours 20 minutes. Developers credited faster bug detection and reported faulty reviews and irrelevant comments.

    "%73.8 of automated code review comments were labeled as resolved. However, the overall average pull request closure duration increased from five hours 52 minutes to eight hours 20 minutes…"

    Published May 2, 2025self-described: Beko, a multinational home appliance maker: about 238 practitioners across ten projects had a reviewer built on PR-Agent; three projects and 4,335 pull requests analyzed

    Counts toward, pending a recheck

    • Overall signal
    • Real bug catches: Positive
    • Comment noise and wrong findings: Raised as a concern

    Published on

    Talks and videos

    Who

    Organization-wide

    Evidence

    Measured

    Applies to

    Needs a recheck

    Observed on

    In-house AI code review tool based on open source Qodo PR-Agent

24. Positive

    gronky_, Hacker News commenter

    Comment on: Effective AI code suggestions: less is moreHacker News comment

    gronky_'s workplace had recently started using Qodo. They like its walkthrough of code changes.

    Published Jan 29, 2025self-described: Employer that had recently started using Qodo

    Counts toward

    • Overall signal
    • PR summaries and effort labels: Positive

    Published on

    Developer communities

    Who

    Professional team

    Evidence

    Reported

    Applies to

    Still applicable

25. Negative

    don-petry, fleet operator for the petry-projects organization

    Lower the advisory quorum to 5: drop the three reviewers that produce no countable signal (re-file of #1894 AC #3)GitHub issue

    don-petry dropped Qodo from the advisory review quorum after counting zero Qodo reviews across eight consecutive pull requests.

    Published Oct 1, 2026self-described: petry-projects repositories with an automated review quorum

    Counts toward

    • Overall signal
    • Missing reviews and setup: Raised as a concern
    • Does Qodo's reviewer earn a permanent place on the pull request?: Dropped it

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Current

26. Mixed

    Viktor Farcic (vfarcic), repository owner

    Compare Qodo and Greptile reviews and pick oneGitHub issue

    Viktor Farcic runs Qodo beside Greptile and plans to compare valid findings and noise. Qodo usage is unlimited there, but it creates no check run when review finishes.

    Published Sep 23, 2026self-described: dot-agent-deck open source repository

    Counts toward

    • Overall signal
    • Credits, trials, and price: Discussed without concern
    • Missing reviews and setup: Raised as a concern

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

27. Negative

    Victor Lyuboslavsky (getvictor), Victor Lyuboslavsky, Fleet Device Management (RawTrail, formerly fleet-edr)

    Run PR-Agent from CI instead of the metered Qodo reviewGitHub issue

    Victor Lyuboslavsky estimated US$590 to US$895 a month under Qodo's credit pricing, against US$38 on the old plan. Self-hosted PR-Agent replaced it, reviewing on pull request open for about US$27 a month in model tokens.

    Published Sep 21, 2026self-described: fleet-edr, a public repository that merged 227 pull requests in 30 days with Qodo reviewing every push

    Counts toward

    • Overall signal
    • Value for Money: Mixed or negative
    • Credits, trials, and price: Raised as a concern
    • Self-hosting on your own model keys matters
    • Does Qodo's reviewer earn a permanent place on the pull request?: Dropped it

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Current

    Observed on

    Qodo after its move to a US$30 base plan with pooled monthly credit packs; open source PR-Agent v0.46.0

28. Mixed

    Fooftilly, repository owner

    chore: suppress empty Qodo review commentsGitHub pull request

    Fooftilly kept Qodo but configured it to skip review and improve comments when it has no material suggestions. The change cuts comments with nothing to act on.

    Published Sep 20, 2026self-described: PRKS repository

    Counts toward

    • Overall signal
    • Configurable review rules: Positive
    • Comment noise and wrong findings: Raised as a concern
    • Does Qodo's reviewer earn a permanent place on the pull request?: Kept it

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

29. Mixed

    blehnen, Maintainer of DotNetWorkQueue

    Evaluate a replacement for qodo PR review (trial ended)GitHub issue

    The maintainer lost Qodo when the trial ended. Across two pull requests, it caught one excellent bug CodeRabbit missed and raised three false positives against documented conventions.

    Published Sep 17, 2026self-described: DotNetWorkQueue, an open source .NET library below Qodo's 200-star open source threshold

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • Comment noise and wrong findings: Raised as a concern
    • Credits, trials, and price: Raised as a concern
    • Does Qodo's reviewer earn a permanent place on the pull request?: Dropped it

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

    Observed on

    Qodo trial on two pull requests

30. Mixed

    ekson73, repository owner

    fix(.pr_agent.toml): contain Qodo skill-insight/cross-repo leak of private-repo contentGitHub pull request

    Qodo skill-insight findings on four PRs cited paths inside a private downstream repository. The owner disabled skills and cross-repo agents in this repository's config.

    Published Sep 14, 2026self-described: multi-agent-os repository with a private downstream repository

    Counts toward

    • Overall signal
    • Configurable review rules: Positive
    • Security and data exposure: Raised as a concern

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

31. Mixed

    auroraxo, PR-Agent contributor

    Qodo review bot has failed on every recent PR since Aug 29GitHub issue

    A contributor counted 195 failed Qodo bot reviews out of 195 on the PR-Agent repository's newest pull requests over about 11 days. Manual retries also failed until a maintainer fixed the cause.

    Published Sep 10, 2026self-described: The PR-Agent repository, which runs Qodo's hosted review bot on its own pull requests

    Counts toward

    • Overall signal
    • Missing reviews and setup: Raised as a concern

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Current

32. Mixed

    ptr727, repository owner

    Qodo No Longer Reviews This Repository, and Two Documents and the Review Script Still Assume It DoesGitHub issue

    ptr727 counted no Qodo reviews on the repository's last 50 PRs. The paid identity posted only a trial-ended notice, and the free identity reviewed only star-qualified repositories.

    Published Sep 9, 2026self-described: ProjectTemplate and sibling public repositories run by one maintainer

    Counts toward

    • Overall signal
    • Credits, trials, and price: Raised as a concern
    • Missing reviews and setup: Raised as a concern

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Current

33. Positive

    Javier C., reviewer on G2

    A Huge Help for Code Reviews, Bug Catching, and Pull RequestsG2 review, syndicated on AWS Marketplace

    Javier C. rates Qodo 5 of 5 for catching bugs across dependencies and files at work. They still check the code because they do not fully trust it.

    Published Sep 3, 2026self-described: Reviews of their own code at work, alongside Copilot

    Counts toward

    • Overall signal
    • Real bug catches: Positive

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

34. Positive

    Dheeraj J., reviewer on G2

    PR-Agent Learns from Past Merges and Integrates Seamlessly with GitHubG2 review, syndicated on AWS Marketplace

    Dheeraj J. rates PR-Agent 4.5 of 5. It learns from past merges and accepted suggestions to avoid repeated comments on each push. Self-hosting adds setup and maintenance work.

    Published Sep 1, 2026self-described: Self-hosted PR-Agent on GitHub

    Counts toward

    • Overall signal
    • Configurable review rules: Positive
    • Missing reviews and setup: Raised as a concern
    • Self-hosting on your own model keys matters

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

35. Mixed

    Pratap J., reviewer on G2

    A Useful Extra Check Before Merging CodeG2 review, syndicated on AWS Marketplace

    Pratap J. rates Qodo 3.5 of 5 as an extra check before finishing a change. Many suggestions do not matter for the change, so they skim for useful ones.

    Published Aug 30, 2026self-described: Reviews of their own changes before calling them finished

    Counts toward

    • Overall signal
    • Comment noise and wrong findings: Raised as a concern
    • A first pass, with humans owning the merge

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

36. Mixed

    Karandeep S., reviewer on G2

    Speeds Up Coding and Reviews, But Struggles with Complex CodeG2 review, syndicated on AWS Marketplace

    Karandeep S. rates Qodo 3.5 of 5. Bug detection speeds review, but complex code receives few suggestions and most miss what they need.

    Published Aug 27, 2026self-described: Reviews of their own code

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • Suggested fixes: Mixed or negative

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

37. Positive

    Sagar K., reviewer on G2

    Qodo Gives My Code a Reliable Second Pair of EyesG2 review, syndicated on AWS Marketplace

    Sagar K. rates Qodo 4 of 5 for catching logic gaps in projects written quickly with AI. It is slow or less accurate with larger context, and its generated tests need fixes.

    Published Aug 23, 2026self-described: Fast-moving personal projects written with coding agents

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • Suggested fixes: Mixed or negative

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

38. Mixed

    Zac O., reviewer on G2

    Invaluable for Code Quality and Repository TrackingG2 review, syndicated on AWS Marketplace

    Zac O. rates Qodo 5 of 5 for tracking issues across repositories. Many suggestions remain generic or unnecessary because Qodo misses their intent.

    Published Aug 23, 2026self-described: Reviews across several repositories

    Counts toward

    • Overall signal
    • Suggested fixes: Mixed or negative
    • Configurable review rules: Positive

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

39. Positive

    Chanchal R., reviewer on G2

    Smart Multi-Agent Reviews That Deliver High-Quality FeedbackG2 review, syndicated on AWS Marketplace

    Chanchal R. rates Qodo 4.5 of 5. Its multi-agent review filters noise down to a few useful comments. It is priced for enterprises and needs rules and indexing before it pays off.

    Published Aug 8, 2026self-described: Qodo multi-agent review with rules and indexed repository history

    Counts toward

    • Overall signal
    • Configurable review rules: Positive
    • Comment noise and wrong findings: Discussed without concern
    • Credits, trials, and price: Raised as a concern

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

40. Positive

    Akash S., reviewer on G2

    Essential Tool for Code Review with Easy SetupG2 review, syndicated on AWS Marketplace

    Akash S. rates Qodo 4 of 5 as a second opinion on pull requests. It catches bugs and edge cases in larger features, but they want better context understanding.

    Published Jul 31, 2026self-described: Reviews of their own pull requests on larger features

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • A first pass, with humans owning the merge

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

41. Positive

    kstruck, repository owner

    docs(process): qodo is BACK - check it on every PR, alongside codexGitHub pull request

    kstruck restored Qodo as a required reviewer beside Codex on every PR. The watcher relies on timing because Qodo emits no completion signal.

    Published Jul 30, 2026self-described: MMPoolsV3 repository

    Counts toward

    • Overall signal
    • Missing reviews and setup: Raised as a concern
    • Does Qodo's reviewer earn a permanent place on the pull request?: Kept it

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

42. Mixed

    Orlando T., reviewer on G2

    Finds Bugs Fast, Lets Reviewers Focus on the Bigger PictureG2 review, syndicated on AWS Marketplace

    Orlando T. rates Qodo 3.5 of 5. Bug catches let reviewers focus on the whole change, but it also hallucinates and produces false positives.

    Published Jul 29, 2026self-described: Code review

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • Comment noise and wrong findings: Raised as a concern

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

43. Positive

    Reinfried B., reviewer on G2

    My Code Reviewer While Building sphragio.ai SoloG2 review, syndicated on AWS Marketplace

    Reinfried B. rates Qodo 5 of 5. The solo founder has it review every pull request before merging by hand. It catches edge cases and inconsistencies they would miss.

    Published Jul 27, 2026self-described: Solo founder of sphragio.ai, a Django and FastAPI SaaS

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • A first pass, with humans owning the merge

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

44. Positive

    mbjorke, repository owner

    Rename kanin-loop → review loop (multi-reviewer: CodeRabbit + Qodo)GitHub issue comment

    mbjorke runs Qodo when CodeRabbit hits its rate limit. Qodo caught a real client-name leak during one of those gaps.

    Published Jul 22, 2026self-described: timelog-extract repository with a multi-reviewer loop

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • Does Qodo's reviewer earn a permanent place on the pull request?: Kept it

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

45. Negative

    Ben C., reviewer on G2, self-described

    Fast and Confident, but Accuracy Falls Short on Larger TasksG2 review, syndicated on AWS Marketplace

    Ben C. rates Qodo 0.5 of 5. It responds fast and confidently but makes several mistakes on larger tasks. It has not solved a problem for them.

    Published Jul 10, 2026

    Counts toward

    • Overall signal
    • Suggested fixes: Mixed or negative

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

46. Positive

    Mike Cann, Convex

    Comparing 9 Code Review Tools - Which is Best?Engineering blog post, Convex Stack (Convex engineering blog)

    Mike Cann scored nine reviewers on ten seeded bugs. Qodo ranked first at 32 of 40 and caught nine primary issues. It fell for a fake N+1 trap and had the worst dashboard, and Cann chose Copilot for daily work.

    Published Mar 10, 2026self-described: Ten seeded pull requests on a React, Vite, and Convex project, scored against nine review bots; video version published March 10, 2026

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • Value for Money: Positive
    • Dashboard and setup friction: Raised as a concern
    • Comment noise and wrong findings: Discussed without concern
    • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer another

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Measured

    Applies to

    Current

47. Negative

    mdeeks, Hacker News commenter

    Comment on: A real-world benchmark for AI code reviewHacker News comment

    mdeeks values price over Qodo's benchmark lead. They report that Cursor's Bugbot costs about the same and offers ten times Qodo's monthly quota.

    Published Feb 4, 2026self-described: Comparing review tools on price and quota

    Counts toward

    • Overall signal
    • Value for Money: Mixed or negative
    • Credits, trials, and price: Raised as a concern
    • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer another

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

    Observed on

    Qodo pricing in February 2026

48. Mixed

    joshgachnang, Hacker News commenter

    Comment on: Devin Review: AI to Stop SlopHacker News comment

    joshgachnang finds high noise ratios in Copilot and Qodo reviews, with occasional legitimate bug catches.

    Published Jan 21, 2026self-described: CTO and founder of Flourish Health, adolescent mental healthcare

    Counts toward

    • Overall signal
    • Real bug catches: Positive
    • Comment noise and wrong findings: Raised as a concern

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

49. Negative

    Nils Amiet, Senior Security Researcher at Kudelski Security

    How We Exploited Qodo: From a PR Comment to RCE and an AWS Admin Key - Leaked TwiceSecurity research, Kudelski Security Research Center

    Nils Amiet showed how a PR comment led to code execution on Qodo Merge Pro's GitHub app server and exposed an AWS administrator key twice. Qodo fixed the issues by October 2025.

    Published Jan 15, 2026self-described: Security research on Qodo Merge and Qodo Merge Pro

    Counts toward

    • Overall signal
    • Security and data exposure: Raised as a concern

    Published on

    Engineering blogs and reviews

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Current

    Observed on

    Qodo Merge Pro GitHub app

50. Negative

    esafak, Hacker News commenter

    Comment on a Hacker News thread (story no longer available)Hacker News comment

    esafak left Qodo after finding little activity on GitHub or Discord. JetBrains plugin releases contained only media files, and issues were piling up.

    Published Nov 10, 2025self-described: Evaluating tools for own use

    Counts toward nothing current

    Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Out of date

51. Positive

    lirantal, Hacker News commenter, self-described

    Comment on: Qodo CLI agent scores 71.2% on SWE-bench VerifiedHacker News comment

    lirantal updated to Qodo Command CLI and liked its permission toggle for read, write, and execute access. They see it as reassurance for security-minded teams adopting coding agents.

    Published Aug 13, 2025

    Counts toward nothing current

    Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Out of date

    Observed on

    Qodo Command CLI

52. Mixed

    afro88, Hacker News commenter

    Comment on: Qodo CLI agent scores 71.2% on SWE-bench VerifiedHacker News comment

    afro88 asks for a plan between the free tier and team plans. They say 250 credits a month runs out too fast for an individual.

    Published Aug 12, 2025self-described: Individual use

    Counts toward nothing current

    Replaced by newer evidence. Kept in the source history with its scope stated; it takes part in no current figure.

    Published on

    Developer communities

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Out of date

    Observed on

    Free plan, 250 credits a month

53. Positive

    Viktor Farcic, DevOps & AI Toolkit

    Better Code Reviews with AI? GitHub Copilot and Qodo Merge TestedVideo, YouTube (DevOps & AI Toolkit)

    Viktor Farcic compared Qodo Merge and Copilot code review on the same pull request. Qodo found more real issues and better fixes. Copilot presented them more clearly, but Farcic would choose Qodo.

    "…differences. The major differentiating factors are that code is a bit better at finding actual issues and proposing solutions, while the way Copilot organizes the information is better and easier to digest. If I would have to choose only one of those two, well, Kodo…"

    Published Jun 30, 2025self-described: Hands-on comparison on one of their own pull requests, with Copilot code review as the existing reviewer

    Counts toward

    • Overall signal
    • PR summaries and effort labels: Positive
    • Real bug catches: Positive
    • Suggested fixes: Positive
    • Comment noise and wrong findings: Raised as a concern
    • Compared hands-on, do practitioners prefer Qodo or another reviewer?: Prefer Qodo

    Published on

    Talks and videos

    Who

    Individual practitioner

    Evidence

    Reported

    Applies to

    Still applicable