AI Agent Index
ByHeather MacAvelia·Independently reviewed·Published Sep 28, 2026·Updated Sep 28, 2026
Independently verified against live vendor data on Sep 28, 2026.

AI code review agent for pull requests, the IDE and the CLI on GitHub, GitLab, Azure DevOps and Bitbucket, with Triage and a Slack agent. From $24/developer/mo billed annually (USD).

How we scored it

Autonomy

4/5

Integrations

5/5

Pricing clarity

4/5

Evidence

4/5

Setup

5/5

The facts

CodeRabbit is an AI code review agent that reviews every pull request within minutes of it being opened, using multiple AI models to summarize the change, comment line by line and suggest one-click fixes. The same reviews run before a commit in the VS Code extension and from the command line, where the CLI can act as a review gate for coding agents such as Claude Code, OpenAI Codex and Cursor. Around the review, the product has grown into what CodeRabbit calls Agentic Change Management: Triage prioritizes open pull requests and can merge ready ones or close stale work by rule, Change Stack explains the intent, behavior and dependencies of a change to the reviewer, CodeRabbit Plan turns issues and designs into coding plans for handoff to an agent, and CodeRabbit Agent runs coding tasks, Slack and Discord requests and automations in cloud sandboxes. CodeRabbit connects to GitHub, GitHub Enterprise Server, GitLab (cloud and self-managed), Azure DevOps, Bitbucket Cloud and Bitbucket Data Center. Reviews draw context from Jira and Linear issues, CircleCI and Jenkins build results, more than 50 bundled linters and security analyzers such as Semgrep and TruffleHog, code guideline files such as CLAUDE.md and AGENTS.md, and learnings that teams teach it in chat. It connects to external MCP servers as a context source, with 5 to 20 MCP connections depending on plan. A REST API covers review metrics, learnings, users, seats and audit logs, and API access is listed on the Enterprise plan. Pricing is in US dollars per developer, and the pricing page opens on Annual billing, which saves 20%. Essentials is $24 per developer per month billed annually ($30 monthly), Team is $48 ($60 monthly) and Advanced is $72 ($90 monthly). Enterprise is priced through sales and adds self-hosting, SSO, custom RBAC, audit logging, API access, multi-org support, an SLA with a dedicated customer success manager, and billing through the AWS, GCP or Claude marketplaces. Paid plans start with a 14-day free trial with no credit card, and seats are charged only for developers who open pull requests. A Free plan covers unlimited public and private repositories with pull request summaries and reviews in the IDE and CLI, and open-source projects get Team features free on public repositories. Reviews beyond the hourly per-developer allowance can continue as usage-based reviews at $0.25 per reviewed file under a monthly spending cap, CodeRabbit Agent is billed at $0.40 per agent minute, and full-codebase Security Scans are priced by usage. Essentials does not include Triage, custom pre-merge checks, finishing touches such as unit test generation and merge conflict resolution, or post-merge actions, which start on Team. Blast radius and architectural impact analysis, security review of every pull request and continuous security monitoring start on Advanced. Essentials allows 5 pull request reviews per developer per hour and 5 MCP connections, against 8, 10 and 12 reviews and 10, 15 and 20 connections on Team, Advanced and Enterprise. Self-hosting is Enterprise-only, and CodeRabbit Agent minutes are not included in any review plan. CodeRabbit suits engineering teams that want an automated first review on every pull request across one or more Git platforms, including teams reviewing the output of coding agents. Teams that want to run an open-source pull request agent themselves with their own model keys should consider CodiumAI PR-Agent. Teams whose main need is scanning dependencies, containers and infrastructure code for vulnerabilities should consider Snyk AI, and teams deploying on Vercel that want reviews validated in sandboxes should consider Vercel Agent. Current state Q3 2026: CodeRabbit raised a $143 million Series C at a $1.5 billion valuation on August 12, 2026, co-led by Atomico and Smash Capital, and introduced Agentic Change Management. Essentials and Team are the new names for the former Pro and Pro+ plans at unchanged prices, and Advanced is a new tier. The trust center lists SOC 2 Type II, ISO 27001:2022 and GDPR, CodeRabbit states that it never uses customer code for model training, and it holds zero data retention agreements with OpenAI and Anthropic. CodeRabbit says it serves more than 17,000 customers and 6 million repositories.

Pricing

freemium · $24/mo annual

View pricing ↗

Segment

b2b

Setup

easy

Verified

Sep 28, 2026

Transparency

Mostly Public

Contract

Monthly or Annual

Data training

Not Trained

Human in loop

Optional

Capabilities

agentic-codinggit-nativeideautonomousreporting

Pros & Limitations

Editorial assessment

Pros

  • ✓Reviews run automatically on every pull request across GitHub, GitLab, Azure DevOps and Bitbucket, and the same review runs in VS Code and the CLI before a commit.
  • ✓Context beyond the diff: Jira and Linear issues, CI results, 50+ bundled linters and SAST tools, MCP servers, code guideline files and learnings taught in chat.
  • ✓Trust center lists SOC 2 Type II, ISO 27001:2022 and GDPR, customer code is never used for training, and zero data retention agreements cover OpenAI and Anthropic.

Limitations

  • –Priced per developer who opens pull requests, from $24 a month billed annually on Essentials, with Triage and finishing touches from Team and security review from Advanced.
  • –Hourly review allowances apply per developer, 5 on Essentials. Reviews beyond them cost $0.25 per reviewed file when usage-based billing is turned on.
  • –Self-hosting, SSO, audit logs and API access are Enterprise-only and priced through sales, and CodeRabbit Agent minutes are billed separately at $0.40 each.

Technical Details

Deployment
cloudself-hostedidecli
Model architectureMultiple AI models, with OpenAI and Anthropic listed as AI subprocessors under zero data retention agreements, plus a post-trained NVIDIA Nemotron model for review routing
Avg setup time2 minutes (vendor quickstart: sign up with your Git platform, no credit card, and add repositories)
Autonomous rateReviews every pull request automatically without a per-review approval, and CodeRabbit Agent runs coding tasks and automations in cloud sandboxes. No completion rate is published.
Integrations
GitHubGitHub Enterprise ServerGitLabAzure DevOpsBitbucket CloudBitbucket Data CenterJiraLinearSlackDiscordVS CodeClaude CodeCodexCursorCircleCIJenkinsSemgrepMCP
Security
SOC 2 Type IIISO 27001GDPRCCPA

Similar agents

Rating

4.3/ 5
★★★★★

Editorial score

How we score this →

Recognition

Listed 2026
Embed these on your site →

Built for

DevToolsEnterpriseStartups

Leave a review

Never displayed publicly.

Agent Stacks

See workflow stacks that feature CodeRabbit.

Compare

Related Content

Is this your tool?

Claim this listing free to get your embeddable badges, a review collection link, and the Claimed badge on your listing.

Claim listing →

Free · Every Two Weeks

AI Agent Price & Rating Tracker

Price changes, new agent launches, acquisitions, and rating updates across the AI agent market. Verified against live vendor data, not vendor marketing.

No spam. Unsubscribe anytime. We never share your email.