CodeRabbit
AI code review tool that automatically comments on pull requests and merge requests.
Commenters use it as an automated pull-request reviewer that catches real issues1234, looks at code beyond the diff5 and costs a flat per-developer price.6 The most common complaints are shallow or noisy feedback789 and bugs it misses that other reviewers catch.101112
Why people recommend it
Catches issues · 3
Teams using it at work say it finds a lot of useful problems.
“We use CodeRabbit at work, which catches good stuff.”
“We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.”
Show 1 more
“We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it.”
PR integration · 3
Runs automated reviews directly on GitHub PRs and merge requests.
“I mostly use CodeRabbit via GitHub PR”
“plus automated reviews from coderabbit in the repo”
Show 1 more
“I use AI-powered auto-complete, search and CodeRabbit for MRs.”
Pricing · 2
Seen as a good deal at a flat $30/month per developer, and free for open source projects.
“We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.”
“Congrats to the CodeRabbit team.”
Wider context · 1
Aware of files outside the diff and the rest of the edited file.
“i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff”
Large PR UI · 1
A newer review interface groups files together, which helps with big PRs.
“We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.”
Caveats and dissent
Missed bugs · 3
Some found bugs and vulnerabilities that slipped past its reviews.
“finds bugs missed by coderabitai, devin-integration-bot, codex and copilot”
“no problem with CodeRabbit”
Show 1 more
“coderabbit being the worst while (presumeably) advertising the most”
Superficial reviews · 2
Mostly flags typos and small errors and does not address architecture or the substance of a change.
“I used CodeRabbit at work, and I have mixed feelings about it.”
“I have similar experience with coderabbit we use at work.”
False positives · 1
One team stopped relying on it after it flagged mostly false positives.
“we use CodeRabbit with Azure DevOps and it flags a lot of things and mostly they were false positives so eventually we stopped relying on it.”
Over-trust · 1
Developers may treat its comments as gospel and harm their code.
“I used CodeRabbit at work, and I have mixed feelings about it.”
Marketing skepticism · 2
Some doubt its advertised claims and dislike its advertising.
“coderabbit being the worst while (presumeably) advertising the most”
“I used CodeRabbit at work, and I have mixed feelings about it.”
Often compared with
Who recommends it in their own words
From the makers not counted in the ranking
“Coderabbit DX staff here. We have a new interface we are exploring for code review called change stack.”
Threads where it came up
- Ask HN: What AI tools help me understand a MR? 1 mention
- Ask HN: How are you all ensuring your AI code isn't slop? 1 mention
- Show HN: Deslop – Oxlint rules for AI-generated TypeScript 1 mention
- Workspace MCP v2 – Musings from the past 18 months building open source AI tools 1 mention
- There is more to code review than (automatable) detection 1 mention
- GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review? 1 mention
Data: coderabbit.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 21
“Would recommend checking out coderabbit change stack. it essentially does exactly what you're looking for”
“I’m also using SonarQube and CodeRabbit”
“I started down this path after looking at what coderabbit suggested”
“plus automated reviews from coderabbit in the repo”
“I have similar experience with coderabbit we use at work.”
“finds bugs missed by coderabitai, devin-integration-bot, codex and copilot”
“no problem with CodeRabbit”
“I used CodeRabbit at work, and I have mixed feelings about it.”
“We use CodeRabbit at work, which catches good stuff.”
“Congrats to the CodeRabbit team.”
“I use CodeRabbit all the time but it has a swarm of dozens of sub-agents.”
“I use AI-powered auto-complete, search and CodeRabbit for MRs.”
“we use CodeRabbit with Azure DevOps and it flags a lot of things and mostly they were false positives so eventually we stopped relying on it.”
“I mostly use CodeRabbit via GitHub PR”
“code rabit or any other code review tool”
“We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.”
“Then I have both Claude and CodeRabbit do code review passes”
“coderabbit being the worst while (presumeably) advertising the most”
“i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff”
“How many more bugs does it produce if we use CodeRabbit to review PRs?”
“We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it.”