Skip to content
← Tools / Skills
ToolCodeRabbit/10 trustMetrics-checked
CodeRabbit logo

CodeRabbit

AI code reviewer that posts summaries and line-level feedback on every pull request.

Visit official site →

About

CodeRabbit is an AI PR review bot that automatically reviews pull requests when they open and on new commits, posting summaries, walkthroughs, and inline comments with one-click fixes. It bundles 40+ linters and SAST scanners, learns from your team's feedback to cut noise over time, and can be driven with @coderabbitai commands in the PR thread. It supports GitHub, GitLab, Bitbucket, and Azure DevOps, with IDE and CLI review modes, and is free for open-source projects. Paid plans start around $24 per developer per month billed annually, with hourly review rate limits on lower tiers, and self-hosting is enterprise-only.

What it can do

  • Automatic PR reviews on open and push
  • PR summaries and walkthroughs
  • Inline comments with one-click AI fixes
  • 40+ bundled linters and SAST scanners
  • Learns from team feedback to reduce noise
  • IDE and CLI review modes
  • @coderabbitai chat inside PR threads
  • Jira and Linear integrations

Setup

  1. Install the CodeRabbit app on your GitHub, GitLab, Bitbucket, or Azure DevOps organization.
  2. Add a .coderabbit.yaml to encode your review conventions and path instructions.
  3. Reviews run automatically on new PRs; use @coderabbitai review for on-demand runs.
  4. Tune noise by reacting to comments so it learns your preferences.

Prerequisites

A git host account (GitHub, GitLab, Bitbucket, or Azure DevOps); a CodeRabbit account for private repos.

Use cases

codeautomation

Works with

Any agent (.md)

Trust score — 7/10

/10 trustMetrics-checked

Scored 7/10 (metrics tier, metrics-v1). Evidence: Very wide adoption; vendor claims most-installed AI app on GitHub; free tier for open source drives volume.; Actively developed: IDE/CLI reviews, agentic chat, MCP connections, usage-based add-ons through 2026.; Closed-source commercial product; self-hosting restricted to large enterprise plans.; Honest caveats: hourly review rate limits on lower tiers; early PRs can be noisy before learnings kick in.. License: Proprietary SaaS; no public source license..

How the trust score is built

Full methodology →
Adoption · stars/downloads, log-scaled vs peers
9.0/10
Maintenance · recency, releases, issue load
8.0/10
Openness · license + docs
2.0/10
Manual review · sanity read + red-flag check
7.0/10
  • · Very wide adoption; vendor claims most-installed AI app on GitHub; free tier for open source drives volume.
  • · Actively developed: IDE/CLI reviews, agentic chat, MCP connections, usage-based add-ons through 2026.
  • · Closed-source commercial product; self-hosting restricted to large enterprise plans.
  • · Honest caveats: hourly review rate limits on lower tiers; early PRs can be noisy before learnings kick in.

Sources

Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.