CodeRabbit 🤖 Agent Freemium

What it does

CodeRabbit is an AI code review service. When a pull request is opened, it analyses the change and posts a plain-language summary in the description, a walkthrough comment and line-by-line review comments, and you can reply to it in the thread to ask questions or request changes. Because it reviews the diff rather than the tool that wrote it, it fits after any coding agent in this directory.

What is inside / how it works

Beyond the core pull request review, CodeRabbit offers one-click fixes and an autofix action that commits fixes for unresolved findings, plus "finishing touches" such as unit test generation, merge conflict resolution, docstrings and code simplification on higher plans. It runs more than 50 linters and security analysers alongside its own analysis, applies guideline files like CLAUDE.md, .cursorrules and AGENTS.md as review criteria, remembers preferences you teach it in chat, and can pull extra context from MCP servers and linked Jira or Linear issues. Newer additions include a cross-repository Triage queue and security scanning.

Works with

Pull request reviews run on GitHub, GitLab, Bitbucket and Azure DevOps. An IDE extension works in VS Code, Cursor, Windsurf and other VS Code-based editors, and a CLI reviews local changes before you push. The CLI is documented as a Claude Code plugin or skill and integrates with Cursor, Codex, Gemini and other agents, so an agent can review its own work.

How to install or start

Pull request reviews are set up by signing up and installing the app on your Git provider. The CLI installs with a script or Homebrew:

curl -fsSL https://cli.coderabbit.ai/install.sh | sh
cr auth login
coderabbit review

Pricing

At the time of writing (September 2026), public repositories get free reviews permanently. Paid plans are per developer: Essentials costs $30 per month ($24 billed annually), Team $60 ($48 annually) and Advanced $72 per month billed annually, with custom Enterprise pricing. All plans include a 14-day trial, and extra usage-based reviews and the cloud agent are billed separately.

Who should use it

Teams merging a lot of AI-written code who want a consistent second reviewer. Expect some noise until you tune its configuration, and per-developer pricing adds up for larger private teams.