CodeRabbit
AI code review agent for GitHub, GitLab, Azure DevOps and Bitbucket with review rules customized in YAML, automatic approvals under risk limits, a cross repository Triage queue, learning loops and enterprise self hosting.
CodeRabbit is an AI code review agent for GitHub, GitLab, Azure DevOps and Bitbucket. It 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, in a terminal CLI, and inside coding agents such as Claude Code, Codex, Cursor and Gemini CLI through plugins and skills. Its homepage reports 17,000 customers and 6 million repositories.
The review runs in several stages. A PR Walkthrough summarizes the change with tables and sequence diagrams, and 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 follow up actions after the review: Fix comments repairs the comments you pick, and fixing CI failures, resolving merge conflicts and generating unit tests each open a stacked pull request or commit to the branch. Autofix keeps a Coding Agent pull request moving, fixing review feedback and failing checks until it is ready.
Automatic Approvals, off by default, requests changes on actionable findings and approves once they are resolved, with risk limits that keep higher risk changes for human approval, and the CodeRabbit check on GitHub can be made a required check. A Coding Agent, in beta, 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; its plan mode writes a plan that a person approves before any code is written.
Triage ranks every open pull request across repositories into one queue, and Triage rules can merge low risk changes, close stale pull requests and send Slack reminders without a manual step. CodeRabbit Security scans whole repositories on demand or on a schedule, and Runtime Analysis, in closed beta, reproduces a finding in a CodeRabbit coding environment and keeps the evidence. A Slack agent investigates incidents and opens pull requests, and each agent run keeps a history of the commands and tool calls it made.
Reviews are grounded on the customer's own context through a Knowledge Base. It combines Learnings captured from chat, Code Guidelines read from rules files including Claude Code rules, connected issue trackers, MCP connected tools, web search for current library documentation and Multi-Repo Analysis across linked repositories, and CodeRabbit stores a vector index of the customer's code for code base context. Behavior is controlled through YAML or TypeScript configuration, glob scoped path instructions, AST pattern based custom rules and configuration inheritance across repository, organization and workspace levels.
Pricing is public and per developer. Essentials costs $24, Team $48 and Advanced $72 per developer per month billed annually ($30, $60 and $90 monthly). A Free plan covers pull request summaries and reviews in the IDE extension and CLI, paid plans start with a 14 day trial, open source projects get Team features free, and Enterprise is on contact. Reviews past the hourly limits are pay as you go at $1 per credit for four files, and agent minutes are $0.40 each.
Enterprise adds self hosting for teams of five hundred or more seats, company selected SaaS regions, SAML SSO with SCIM, custom RBAC, audit logging and API access. CodeRabbit's Data Processing Addendum states an information security management system that complies with ISO/IEC 27001:2022 and hosting on GCP, and it describes itself as SOC 2 Type II certified. Its trust center at trust.coderabbit.ai runs on Vanta, and the reports are not publicly viewable there. CodeRabbit never uses customer code for training, and self hosted customers can turn all data retention off.
From our AI code reviewers video
AI Code Review Tools: Which Ones Run the Code They Review?
Our video on the 7 AI code reviewers in the index names what each one does best. For CodeRabbit, that is turning review into a gate the team sets.
The player starts at CodeRabbit's part, 0:56 in. Recorded in October 2026; the profile here is live and updates as research is verified.
From our comparison video
CodeRabbit vs Graphite for Teams Whose Pull Requests Pile Up
Our 3 minute video puts CodeRabbit side by side with Graphite. It covers what each one does and how each is priced, then when to choose which.
Recorded in October 2026. The profile here is live and updates as research is verified.
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, a terminal CLI, and plugins for Claude Code, Codex, Cursor, Gemini CLI and Antigravity. More than 50 linters and SAST scanners run alongside the AI review. Saved connections cover Jira, Linear, GitHub and GitLab issues, Jenkins, CircleCI and more than 40 connectors, and MCP server connections pull context from external tools, with 5, 10, 15 or 20 connections by plan. Enterprise adds API access, and the Slack and Discord agents 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 review rules you customize in YAML, 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
12.0 / 14 capabilities · 86%
| Integrations & Tool Calling | Full |
|---|---|
|
Reviews run on GitHub, GitLab, Azure DevOps and Bitbucket, with linked issues from GitHub, GitLab, Jira and Linear, saved connections to more than 40 connectors, MCP servers for outside context, Jenkins and CircleCI build failures, and web search for library documentation. Reviews also run in VS Code and JetBrains, in the CLI, and inside Claude Code, Codex, Cursor, Gemini CLI and Antigravity through plugins and skills. Sourcedocs.coderabbit.ai/knowledge-base, connections and cliread 2026-10-28 |
|
| Workflow Orchestration | Full |
|
Several agents divide the work. Besides the review agent, a research agent checks linked repositories, a Coding Agent turns review findings, plans, security findings or failing CI checks into tasks delivered as commits or stacked pull requests, Autofix keeps fixing review feedback and failing checks until a pull request is ready, and a Slack agent and Triage handle their own jobs, with work passing between the agents. Sourcedocs.coderabbit.ai/code, multi-repo-analysis and the 14 October changelogread 2026-10-28 |
|
| Knowledge Grounding & RAG | Full |
|
CodeRabbit stores vector representations of the customer's code as a code index for code base context, alongside cached code and dependency archives, and its homepage describes a Codegraph mapping every node a change can reach. Reviews also draw on code guidelines from rules files, linked issues and past pull requests, MCP servers, web search and linked repositories. The index is described in one FAQ line with no page on its scope or refresh, and self hosted customers can turn data retention off. Sourcedocs.coderabbit.ai/faq (Code Storage), coderabbit.ai homepage and knowledge-baseread 2026-10-28 |
|
| 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 an implementation plan for a person to approve before any code is written. Automatic Approvals, off by default, requests changes on actionable findings and approves a pull request only once its threads are resolved, the latest commit is reviewed and pre merge checks pass; risk limits withhold approval above a chosen merge or security risk, overrides keep named teams or paths for human approval, and it never merges. Sourcedocs.coderabbit.ai/code and pr-reviews/automatic-approvalsread 2026-10-28 |
|
| Security, Identity & Governance | Full |
|
Enterprise SSO signs users in through Okta, Google Workspace, Microsoft Entra ID or any SAML 2.0 provider, with SCIM directory sync from Okta or Entra ID, workspace and organization roles, custom roles with granular permissions and a tamper resistant audit log. The Data Processing Addendum states an information security management system that complies with ISO/IEC 27001:2022, annual independent risk assessments and hosting on GCP, and the FAQ read on 30 September 2026 stated SOC 2 Type II with annual audits. The trust center at trust.coderabbit.ai runs on Vanta and shows nothing to an automated read, and the FAQ answers now render client side. Sourcedocs.coderabbit.ai/management/sso, custom-roles, audit-logs and coderabbit.ai/legal/dparead 2026-10-28 |
|
| Observability & Auditability | Full |
|
Agent thread reviews keep a run history, with an execution detail layer showing the commands, tool calls and activity of each run, and Runtime Analysis keeps the completed steps, command output and observations of each verification run with the finding. The Usage view logs every run with who triggered it, its scope and its minutes. Enterprise audit logs add administrative changes, with SIEM export through the API. No retention period for run history is stated. Sourcedocs.coderabbit.ai/slack-agent/thread-reviews, security/runtime-verification and management/audit-logsread 2026-10-28 |
|
| 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, held for admin approval when a delay is set, and browsable, editable and deletable in the dashboard or through the API. CodeRabbit Agent for Slack also keeps facts and agent written skills across sessions. Sourcedocs.coderabbit.ai/knowledge-base/learnings and agent/skillsread 2026-10-28 |
|
| 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, with a reverse tunnel for platforms that accept no inbound connection. The cloud service runs on GCP, Enterprise lists company selected SaaS regions among its deployment options, and the CLI signs in to a US or EU region. Sourcedocs.coderabbit.ai/self-hosted/overview, coderabbit.ai/pricing and the CLI v0.7.2 changelogread 2026-10-28 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
The review agent's built in follow up actions are Finishing Touches (Fix comments, fixing CI failures, resolving merge conflicts, generating unit tests and docstrings, simplifying code), pre merge checks and Post-Merge Actions, and Triage ships five starter rule templates covering low risk merges, auto fixes, stale pull requests, Slack reminders and urgent fixes. Customers write their own recipes, checks and skills, and there is no library of prebuilt agents. Sourcedocs.coderabbit.ai/finishing-touches, triage/rules and pr-reviews/post-merge-actionsread 2026-10-28 |
|
| Triggers & Channel Coverage | Full |
|
Reviews run automatically when a pull request opens and on later pushes, the Coding Agent can start from a failing CI check or a security finding, Triage rules act on pull requests that match conditions without a person touching each one, Post-Merge Actions run after a merge, and Slack automations fire on schedules, webhooks and PagerDuty incidents. Comments, the IDE and the CLI let people request runs too. Sourcedocs.coderabbit.ai/code, triage/rules and slack-agent/automationsread 2026-10-28 |
|
| Model Flexibility & Routing | Full |
|
Self hosted CodeRabbit connects to the customer's own LLM provider or account under the customer's own keys, while the cloud service sends code to OpenAI and Anthropic models of its own choosing. Sourcedocs.coderabbit.ai/self-hosted/overview and faqread 2026-10-28 |
|
| 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, Deep Scan findings, organizations and repositories, metrics, learnings, users and roles, and audit log export, with an OpenAPI spec published. Most endpoints are Enterprise plan features with public documentation; since 1 October 2026 the Deep Scan findings endpoint is open to every plan with a non agentic key. Sourcedocs.coderabbit.ai/api, api-reference and changelogread 2026-10-28 |
|
| Testing, Debugging & Optimization | Partial |
|
Finishing Touches generate unit tests and fix CI failures in the customer's code, Runtime Analysis, in closed beta on GitHub Cloud, runs a reproduction of a Deep Scan finding in a CodeRabbit coding environment and keeps the evidence, and the CLI's severity gate exits non zero on major findings so scripts can block. All of it tests the customer's code; there is no harness to evaluate or regression test the review agent's own behavior. Sourcedocs.coderabbit.ai/finishing-touches, security/runtime-verification and cli/referenceread 2026-10-28 |
|
| Browser & Computer Use | Not documented |
|
Agents work through Git platform APIs, the IDE, the CLI and a cloud coding environment for coding tasks and runtime verification. Browser control and operation of software through a graphical interface are not described. Sourcedocs.coderabbit.airead 2026-10-28 |
|
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
Product updates
The CodeRabbit API now exposes more than 150 product operations covering pull request reads and review requests, Coding Agent tasks and plan approval, Triage priority and rules, security scans and AI fixes, Learnings, agent automations, settings and usage. The same operations are tools on a hosted MCP server at mcp.coderabbit.ai that Claude, Claude Code, Codex and other MCP clients can connect to with OAuth, acting with the signed in user's permissions. A coderabbit api request CLI command calls any operation from a shell or CI job.
Bears on: MCP / tool calling / API
View sourceRisk instructions let teams describe in plain language what is risky and what is routine in their codebase. Combined with Automatic Approvals and a merge risk limit, CodeRabbit approves routine pull requests and holds back the ones the instructions flag; on GitHub Cloud with the Team plan or higher, a Triage rule can then merge the approved pull requests. A CodeRabbit plugin for JetBrains IDEs also entered public beta on the JetBrains Marketplace.
Bears on: Human approval / guardrails
View sourceFailed pipeline jobs on GitLab Cloud merge requests can now go straight to the Fix CI agent in CodeRabbit. A comment of @coderabbitai fix-ci returns the fix as a stacked merge request, and adding the word commit puts it on the source branch instead.
Bears on: Integrations
View sourcePricing
From $24 per developer per month billed annually on Essentials ($30 monthly). A Free plan covers pull request summaries, and paid plans start with a 14 day trial.
Per developer seats, plus metered usage for reviews beyond the hourly limits and for Coding Agent minutes.
Included quota
Each developer gets an hourly review limit of 5 on Essentials, 8 on Team, 10 on Advanced and 12 on Enterprise, subject to fair use.
What is public
Annual per developer prices for Essentials, Team and Advanced ($24, $48 and $72), monthly prices in the docs ($30, $60 and $90), the hourly review limits, the pay as you go review rate ($1 per credit, 4 files per credit), the $0.40 per agent minute rate, linked repository and MCP connection limits by plan, and the 14 day trial are published. A Free plan with pull request summaries is described in the docs, 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 price per developer. On top of the seats, CodeRabbit meters reviews beyond each plan's hourly limit, billed pay as you go, and Coding Agent minutes at $0.40 each. The bill grows with review volume above the limits and with how long the Coding Agent runs. Optional monthly spending caps on Essentials through Advanced limit the review overage, and trial and free minutes are used before paid Coding Agent minutes.
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 at $1 per credit, with 4 files reviewed per credit ($0.25 a file), and an optional monthly spending cap on Essentials through Advanced. Agent minutes for the Coding Agent, CodeRabbit Agent and Runtime Analysis are billed at $0.40 per minute after free turns and trial credits.
Sales call required
No, self serve available
Free / trial
Free plan with pull request summaries and reviews in the VS Code extension and CLI, a 14 day trial of the paid plans with no card required, and free reviews 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
CodeRabbit renamed its plans, with Pro and Pro+ becoming Essentials, Team and Advanced. The Free plan is described in the docs rather than on the pricing page. The pricing page now sells five named products (Review, Triage, Explain, Secure and Engineer) and lists Deep Scan and CodeRabbit Engineer as on demand products without a rate; the $0.40 per agent minute figure sits on the docs runtime verification page, and the FAQ answers on coderabbit.ai render client side.
Cancellation / refund
Annual billing saves 20 percent against monthly. Enterprise is contracted through sales.
Support SLA / resale
Enterprise adds SLA support, technical enablement and a dedicated CSM.
Missing data
Monthly billing prices and Enterprise pricing are not published.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- 10Web — Agentic website platform whose AI agents build, host and manage…
- AgentUI — Managed AI app builder for operations teams that generates and hosts…
- Aider — Open source, model agnostic terminal coding agent that edits your…
- Amp — Amp is a coding agent from Amp Frontier Corporation that runs each…
- Anthropic Claude Code — Anthropic's agentic coding system across terminal, desktop, IDE, web…
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.
- Tabnine11.5 / 14A lighter documented profile than CodeRabbit
- Augment Code12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Poolside11.0 / 14A lighter documented profile than CodeRabbit
- Cognition13.5 / 14Adds documented Browser & Computer Use
- Ellipsis10.5 / 14A lighter documented profile than CodeRabbitCodeRabbit vs Ellipsis →
- GitHub Copilot13.5 / 14Adds documented Browser & Computer Use
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded