CodeRabbit
AI code review agent for GitHub and GitLab with YAML-customizable review rules, PR analytics, learning loops, and enterprise server deployment support.
CodeRabbit is an AI code review agent for GitHub, GitLab, Azure DevOps and Bitbucket that reviews pull requests automatically and posts line by line feedback with severity labels, alongside a structured walkthrough summarizing the change. It also runs in VS Code and JetBrains IDEs and in a terminal CLI, and reports over two million connected repositories and more than thirteen million pull requests processed.
The review chains several stages rather than emitting a single comment.
A PR Walkthrough summarizes the change with tables and sequence diagrams, the line by line review flags bugs, security issues and style problems with one click fixes, custom Pre-Merge Checks act as organization defined gating checks, and Finishing Touches run post review agentic actions including autofix, fixing CI failures, resolving merge conflicts and unit test generation.
A Coding Agent turns a request, a review finding, a plan or a failing CI check into a task it implements in the cloud and delivers as a commit or stacked pull request, with a plan mode whose written plan a person approves before any code is written, and a Slack agent investigates issues and opens pull requests.
Reviews are grounded on the customer's own context through a Knowledge Base combining Learnings captured from chat, Code Guidelines, connected issue trackers, MCP connected tools and Multi-Repo Analysis across linked repositories, with web search for current library documentation. Behavior is controlled through YAML configuration, glob scoped path instructions, AST pattern based custom rules and configuration inheritance across repository and organization levels.
Pricing is per developer and public: Essentials at twenty four dollars, Team at forty eight and Advanced at seventy two per developer per month billed annually, with a 14 day free trial, a free plan for open source projects and Enterprise on contact. Enterprise adds self hosting for teams of five hundred or more seats, SSO, custom RBAC, audit logging and API access. The company is SOC 2 Type II and ISO 27001:2022 certified with reports published on its trust center, processes code in an ephemeral environment destroyed after each review, and holds a zero data retention amendment with its LLM providers.
Vendor details
Canonical URL
https://coderabbit.ai
Category
Coding agent
Company status
independent
Use cases & customers
Target customers
Deployment options
Integrations
Reviews run on GitHub, GitLab, Azure DevOps and Bitbucket, plus VS Code and JetBrains IDE extensions and a terminal CLI. Over forty linters and SAST scanners run alongside the AI review, issue trackers including Linear, Jira, GitHub Issues and GitLab feed the Knowledge Base, and MCP server connections pull context from external tools, with five, fifteen or twenty connections by plan. Enterprise adds API access, and a Slack agent can investigate issues and open pull requests.
In practice
Pull requests pile up waiting for a human reviewer. CodeRabbit reviews PRs automatically on GitHub and GitLab, so feedback lands without waiting on a teammate.
Generic review bots flag noise that doesn't match your team's standards. CodeRabbit takes YAML-customizable rules, so reviews follow the conventions your team actually enforces.
Your reviewer keeps catching the same issues across PRs. CodeRabbit has learning loops, so its review adapts to your codebase instead of repeating generic comments.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool Calling | Full |
|---|---|
|
Reviews run on GitHub, GitLab, Azure DevOps and Bitbucket, with linked issues from GitHub, GitLab, Jira and Linear, MCP servers for outside context and web search for library documentation, plus IDE and CLI reviews. Sourcedocs.coderabbit.ai/knowledge-base and self-hosted overviewread 2026-09-29 |
|
| Workflow Orchestration | Full |
|
Several agents divide the work: the review agent, a research agent that checks linked repositories, a Coding Agent that turns review findings, plans, security findings or failing CI checks into tasks delivered as commits or stacked pull requests, a Slack agent and Triage, so work passes between agents. Sourcedocs.coderabbit.ai/code, multi-repo-analysis and llms.txtread 2026-09-29 |
|
| Knowledge Grounding & RAG | Partial |
|
Reviews draw on code guidelines detected from rules files, linked issues, MCP servers, web search and linked repositories, but multi repo analysis reads the linked repositories per review and no persistent index or code graph is documented. Sourcedocs.coderabbit.ai/knowledge-base and multi-repo-analysisread 2026-09-29 |
|
| Human Oversight & Guardrails | Full |
|
The Coding Agent's code mode produces a proposed patch that requires manual review before delivery, and its plan mode writes a versioned implementation plan for a person to approve before any code is written, after which the agent implements only what was authorized. Sourcedocs.coderabbit.ai/coderead 2026-09-29 |
|
| Security, Identity & Governance | Full |
|
The FAQ states CodeRabbit is SOC 2 Type II certified and GDPR compliant, the landing and security pages state annual independent SOC 2 Type II audits, and the plans documentation lists SSO, custom RBAC and audit logging on Enterprise alongside self hosting. The trust center at trust.coderabbit.ai is hosted on Vanta, and neither the SOC 2 report nor an ISO 27001 statement is publicly viewable there. Sourcecoderabbit.ai/faqread 2026-09-30 |
|
| Observability & Auditability | Partial |
|
Enterprise audit logs record administrative changes to organizations, repositories, seats, configuration, roles, API keys and knowledge bases and export to a SIEM through the API, and a metrics API and reports cover review activity; a per run record of the agent's own tool calls and reasoning is not documented. Sourcedocs.coderabbit.ai/management/audit-logs and apiread 2026-09-29 |
|
| Memory & State Persistence | Full |
|
Learnings are created by CodeRabbit from team chat during reviews and stored in its database, scoped to the organization or a repository, kept until deleted with never used learnings flagged for review, and browsable, editable and deletable in the dashboard or through the API. Sourcedocs.coderabbit.ai/knowledge-base/learningsread 2026-09-29 |
|
| Deployment & Data Residency | Full |
|
Self hosted CodeRabbit, on Enterprise with 500 or more seats, runs inside the customer's own infrastructure on GitHub Enterprise Server, GitLab self managed, Azure DevOps and Bitbucket Data Center, keeping code, pull request data and review traffic inside a boundary the customer controls, for data residency and air gapped needs. Sourcedocs.coderabbit.ai/self-hosted/overviewread 2026-09-29 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
Built in Finishing Touches (autofix, fixing CI failures, resolving merge conflicts and generating unit tests) and built in pre merge checks ship as follow up actions of the review agent, with custom recipes and custom checks the customer writes; these are features and customer assembled assets rather than a library of prebuilt agents. Sourcedocs.coderabbit.ai llms.txt (finishing touches, pre-merge checks)read 2026-09-29 |
|
| Triggers & Channel Coverage | Full |
|
Reviews run automatically when a pull request opens and on later pushes, and the Coding Agent can start from a failing CI check or a security finding, so work reaches the agents without a person starting it; Slack automations, comments, the IDE and the CLI add requested runs. Sourcedocs.coderabbit.ai/code and pricingread 2026-09-29 |
|
| Model Flexibility & Routing | Full |
|
Self hosted CodeRabbit connects to the customer's own LLM provider or account, so the customer picks the provider under its own keys; the cloud service routes across providers itself. Sourcedocs.coderabbit.ai/self-hosted/overviewread 2026-09-29 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
The CodeRabbit API at api.coderabbit.ai, authenticated with an x-coderabbitai-api-key header and organization, workspace or self hosted scoped keys, covers review data, AI Deep Scan findings, organizations and repositories, metrics, learnings, users and roles, and audit log export; it is an Enterprise plan feature with public documentation. Sourcedocs.coderabbit.ai/apiread 2026-09-29 |
|
| Testing, Debugging & Optimization | Partial |
|
Unit test generation and CI failure fixes are Finishing Touches that test the customer's code, and metrics report review activity; no harness to evaluate or regression test the review agent's behavior is documented. Sourcedocs.coderabbit.ai llms.txt (finishing touches, reports)read 2026-09-29 |
|
| Browser & Computer Use | Not documented |
|
Agents work through Git platform APIs, the IDE, the CLI and a cloud environment for coding tasks; no browser control or operation of software through a graphical interface is documented. Sourcedocs.coderabbit.airead 2026-09-29 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Recent platform changes
New Triage rules in CodeRabbit act on pull requests that match conditions an organization sets. A rule can merge low risk pull requests once checks and reviews pass, close stale ones after notice, send the coding agent to fix failed checks and review feedback, or send Slack reminders.
Bears on: Human approval / guardrails
View sourceCodeRabbit CLI 0.8.1 adds cr code handoff to create a cloud Coding Agent task from a local session summary, with an optional plan and discovered transcript. Handoff output now identifies the branch, commit, transferred files, and cloud task; scripts parsing the earlier output need adjustment.
Bears on: Workflow orchestration
View sourceOrganization administrators can now access conditional rate-limit impact metrics for users and reviews via the Billing and Usage dashboard. The update includes a Most Active Users table and alerts administrators when monthly spend reaches 90 percent of the configured cap.
Bears on: Observability / auditability
View sourcePricing
From $24 per developer per month billed annually (Essentials); 14 day free trial
hybrid
Included quota
Hourly review limits per developer: Essentials 5, Team 8, Advanced 10 and Enterprise 12, subject to fair use.
What is public
Annual per developer prices for Essentials, Team and Advanced, the hourly review limits, the pay as you go review add on, the Coding Agent's per minute rate and the 14 day trial are published; monthly prices are not shown and Enterprise is priced on contact.
Billing mechanics
Per developer subscription with hourly review limits, pay as you go reviews beyond those limits, and the Coding Agent billed by agent minute.
Cost watchouts
Reviews past hourly limits and Coding Agent minutes add usage charges; SSO, custom RBAC, API access and self hosting are Enterprise only.
Variable cost rationale
Seats are a flat per developer price, while over limit reviews and Coding Agent minutes are metered.
Additional watchouts
The Coding Agent and over limit reviews are metered on top of the seat price, and self hosting needs Enterprise with 500 or more seats.
Overage / add-ons
Reviews beyond each plan's hourly limit are pay as you go, with optional monthly spending caps on Essentials through Advanced; the Coding Agent is billed at $0.40 per agent minute after trial minutes.
Sales call required
No, self serve available
Free / trial
14 day free trial on every plan with no credit card; a free plan for open source projects.
Lowest paid plan
Essentials at $24 per developer per month billed annually.
Commercial notes
Open source projects have a free plan, and Enterprise adds custom RBAC, SSO, API access and self hosting.
Key ambiguities
The plans were renamed since the prior record (Pro and Pro+ became Essentials, Team and Advanced) and the free plan for private repositories is no longer listed.
Cancellation / refund
Annual billing saves 20 percent against monthly; Enterprise is contracted through sales.
Missing data
Monthly billing prices and Enterprise pricing are not published on the pricing page.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- 10Web — Agentic website platform whose specialized AI agents build, host,…
- AgentUI — Managed AI app builder for operations teams that generates and hosts…
- Aider — Open source, model agnostic terminal coding agent that edits your…
- Anthropic Claude Code — Anthropic's agentic coding system across terminal, desktop, IDE, web…
- AppFactor — Agentic platform that runs persistent agents across an enterprise…
Alternatives to CodeRabbit
The closest documented capability profiles to CodeRabbit among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- OpenCode10.0 / 14A lighter documented profile than CodeRabbit
- Poolside11.0 / 14Fuller documented coverage on Observability & Auditability
- Ellipsis10.5 / 14Fuller documented coverage on Observability & AuditabilityCodeRabbit vs Ellipsis →
- JetBrains AI10.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Tabnine11.5 / 14Fuller documented coverage on Knowledge Grounding & RAG and Observability & Auditability
- Augment Code12.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Observability & Auditability
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded