CodeRabbit

17 Dec 2025

AI coding assistants are shipping more code...but also more bugs! Our State of AI vs. Human Code Generation Report analyzed 470 real GitHub PRs. The findings? AI‑coauthored PRs produced about 1.7× more issues than human‑only PRs!

Attackers are using AI to find the holes in your code. We’ll help you find and fix them first, for free. Through November 8, $1,000,000 in Deep Scan usage is on us. Current users, former users, teams who've never touched us. First come first served. www.coderabbit.ai/blog/one-mi...

350,666 installs on GitHub marketplace 🎉 400k soon?

luma.comInference on Tap: Berlin @ NVIDIA GTC · LumaJoin Baseten and CodeRabbit for an evening bringing together builders, operators, and curious minds who are pushing AI inference forward. We are taking over…

In Berlin for @nvidia GTC? Join CodeRabbit and @baseten October 21 at Fabrik 23 for Inference on Tap. Talk AI inference and the agentic SDLC over drinks with fellow builders! Request to join: luma.com/baseten-0g1s

AI adoption needs more than a rollout. Announcing DevClarity + CodeRabbit: hands-on AI enablement meets independent code review, helping software teams put AI to work and stay in control of what ships. www.coderabbit.ai/partnership...

coderabbit.aiIntroducing collaborative coding with Slack | CodeRabbitLearn how Slack Code channels and CodeRabbit Agent for Slack bring experts into one shared thread to specify, plan, and build software together.

Coding doesn't have to be a solo chat. Bring your team into Slack Code channels with CodeRabbit Agent for Slack and shape the spec together. Meet collaborative coding: www.coderabbit.ai/blog/introd...

A coding agent can get an authorization check wrong, then write tests that confirm the mistake. Everything passes. That's why the review has to be independent of the system that wrote the change. Here’s how CodeRabbit solves that: www.coderabbit.ai/blog/why-ag...

docs.coderabbit.aiCodeRabbit Documentation - AI code reviews on pull requests, IDE, and CLIComplete documentation for CodeRabbit. AI code reviews, on pull requests, on the IDE, and on the CLI. With deep integrations to Codex, Claude Code, Cursor, and Gemini and more.

This week in the CodeRabbit changelog 🐰 → Share TypeScript review configs across repos → Handle metrics API retries with clearer retry guidance Define review standards once. Reuse them across your team’s repositories. See the full changelog: docs.coderabbit.ai/changelog

TypeScript config docs: docs.coderabbit.ai/configurati... MCP Metrics docs: docs.coderabbit.ai/api-referen... Review Comment Metrics dovs: docs.coderabbit.ai/api-referen...

Know what your PR does. CodeRabbit Change Stack - your explainability layer: > Overview + Layers: map the PR's logical changes > Findings: issues, proposed fixes and agent prompts > Code Peek + AI Chat: definitions, context, answers > Blast radius: understand the impact

coderabbit.aiCodeRabbit Change Stack | Code explainability for massive diffsTurn massive diffs into an understandable, layered review with CodeRabbit Change Stack.

Code explainability for massive diffs: www.coderabbit.ai/change-stack

Agents can create PRs in minutes, but understanding them still takes work. CodeRabbit Change Stack connects a PR's purpose, behavior, dependencies, and code so reviewers can really verify it before approving. Do you understand what you're about to merge?

www.coderabbit.ai/blog/do-you...

coderabbit.aiDo You Understand What You’re About to Merge? | CodeRabbitFive questions every reviewer should answer before approving a pull request, and how Change Stack ties intent, behavior, dependencies, and risk back to the code.

17 Sept

PRs piling up. Which one needs you next? Hop over to see how CodeRabbit Triage can sort the queue for you. Quick walkthrough 👇

docs.coderabbit.ai/triage

17 Sept

coderabbit.aiCodeRabbit Triage: Know Which Pull Request to Review NextCodeRabbit Triage scores and explains pull request priorities so reviewers can focus their attention, route work, and identify the next action.

15 Sept

A list of open PRs can be complete and still not tell you what to do next. > Does this PR need attention now? > What it’s important? > What’s the next action? You shouldn't have to open each PR to find out. www.coderabbit.ai/blog/codera...

9 Sept

Got 5 minutes?

1 Sept

We're experiencing an outage and we are working to resolve it! We'll keep this thread updated when the situation changes & we appreciate your patience!

1 Sept

Before: 20 repos, 20 standards files. Update one and the other 19 go stale. After: one central repo. Point 𝚏𝚒𝚕𝚎𝙿𝚊𝚝𝚝𝚎𝚛𝚗𝚜 at it with 𝚛𝚎𝚙𝚘:𝚙𝚊𝚝𝚑, and CodeRabbit pulls the right standards into every review, in every repo.

1 Sept

Provide your agents with the docs: docs.coderabbit.ai/knowledge-b...

27 Aug

If you already love our Pre-Merge Checks, this is for you. One click and AI fixes the failed ones. We got you.

27 Aug

Read more about Pre-Merge Checks here: docs.coderabbit.ai/pr-reviews/...

coderabbit.aiCodeRabbit commits more than $10 million to open sourceCodeRabbit is committing more than $10 million of its actual direct cost to open source over the next year through cash sponsorships, free Review and Security, and broader agentic support across the software development lifecycle.

26 Aug

langflow. bun. ant-design. nuxt. vue. mermaid. pnpm. trpc. Over 600,000 GitHub stars between them, and CodeRabbit reviews it all, for free. Next stop: more than $10M into OSS over the next year, counted at what it costs us. Heres the how and why 👇 www.coderabbit.ai/blog/codera...

coderabbit.aiCodeRabbit for Open Source | Free AI Code ReviewsCodeRabbit gives open source maintainers free AI code reviews that catch bugs, reduce review burden, and help projects merge pull requests faster.

26 Aug

www.coderabbit.ai/oss

25 Aug

CodeRabbit is now available as a plugin for Cursor! Ask Cursor Agent to review your changes, delegate review to the included CodeRabbit subagent, choose the diff scope, and work through findings without leaving your Agent workflow. Heres a quick overview!

cursor.comCursor Marketplace | Cursor PluginsDiscover verified Cursor plugins including skills, subagents, rules, hooks, commands, and MCP servers.

25 Aug

Install it from the Cursor Marketplace: cursor.com/marketplace

Full code security visibility. Steer it all from the CodeRabbit Security panel. Detect, understand, secure.

docs.coderabbit.ai/security-agent

A diff shows the lines that changed, not what they reach. Blast Radius maps each change against: > Dependencies it uses > Consumers it may affect > Tests that cover it > Supporting repository context It’s included with CodeRabbit Security and available through Change Stack.

To see how it works, open your PR with Change Stack and select Blast Radius from the left sidebar docs.coderabbit.ai/security-ag...

Security issues raised in review land in PR Findings. Change Stack provides the explainability layer. You or your agent takes it from there. Detect, understand, fix.

View full thread

High level view 👇🏾

docs.coderabbit.ai/security-agent

Security issues raised in review land in PR Findings. Change Stack provides the explainability layer. You or your agent takes it from there. Detect, understand, fix.

Where to find them in CodeRabbit web interface: Security > Pull Requests > PR Findings

19 Aug

Agents can write code faster than ever. Review can’t be the bottleneck. CodeRabbit CLI 0.7 makes typical reviews 19% faster, longer reviews up to 23% faster, and cuts client disconnects by 31%. More review-fix-review cycles completed before the code ever reaches a pull request.

docs.coderabbit.ai/changelog/#...

19 Aug

17 Aug

CodeRabbit Security's AI Deep Scan finds exploitable vulnerabilities across your source code and infra config. Every finding: category, severity, CWE, file, line range and reachability. Understand the exploit and fix it yourself or with AI.

17 Aug

How to run an AI Deep Scan 👇 docs.coderabbit.ai/security-ag...

17 Aug

How to run an AI Deep Scan 👇 docs.coderabbit.ai/security-ag...

5 Aug

300,000 installs on GitHub 🎉

github.comCodeRabbit - GitHub MarketplaceCut Code Review Time & Bugs in Half

5 Aug

You can be our 301,170th! github.com/marketplace...

31 July

+ PII leaking into logs. + An auth server error. + A concurrency bug in an idempotency path. CodeRabbit surfaced all three in the systems that protect 1.6M+ customers, before a human even opened the PR. Find out how we managed that (and more use cases) below 👇

www.coderabbit.ai/case-studie...

31 July

coderabbit.aiHow Neo Financial scales code review with CodeRabbitSee how service-specific configuration and shift-left review help Neo Financial keep review velocity steady under heavier AI-assisted PR volume.

30 July

VS Code CodeRabbit extension v0.21.2 is live 🚨 > In-IDE reviews now stay connected and reconnect more reliably during longer sessions. > Sign-in flow improved to help you reach the right workspace. Install or update to take advantage of the latest version ✌️

30 July

Install or update here: docs.coderabbit.ai/ide/vscode-...

20 July

CodeRabbit can now investigate and fix CI failures on GitHub! Once you trigger the action using '@coderabbitai fix-ci', CodeRabbit will investigate, fix, and deliver a stacked PR ✌️ Check out the docs below to get started.

docs.coderabbit.ai/finishing-t...

20 July

16 July

Pattern-based scanners can parse your syntax but they have no idea what your app actually does. That's why the logic flaw ships clean while you burn a sprint triaging a "critical" in dead code. Reasoning and trust across the codebase is the whole game now.

www.coderabbit.ai/blog/hidden...

16 July

coderabbit.aiThe hidden cost of your security stackSecurity tool sprawl creates hidden costs in alerts, context switching, backlogs, and verification work as teams ship more AI-generated code.

13 July

CodeRabbit can now take action AFTER a PR has merged, not just before ✌️ You can configure up to 5 post-merge actions across your org and set them up via Settings > Post-merge actions! (Full docs below)