# CodeRabbit — An AI code-review agent, not a code-writing one — reviews every pull request automatically across GitHub, GitLab, Bitbucket and Azure DevOps, with a genuine free tier for unlimited repos.

> Source: The Agents Index — https://theagentsindex.com/coderabbit (structured, researched, re-verified)
> Facts last verified: 2026-07-24

CodeRabbit is an AI code-review agent that automatically reviews pull requests on GitHub, GitLab, Bitbucket and Azure DevOps, plus commits in VS Code, Cursor and Windsurf via IDE and CLI review — a different job from every other coding-agents listing in this category, which write or generate code rather than review it. It raised a $60M Series B in September 2025 led by Scale Venture Partners, with participation from Nvidia's NVentures and CRV alongside existing investors Harmony Partners, Flex Capital, Engineering Capital and Pelion Venture Partners, valuing the company at roughly $550M on $88M total raised. NVIDIA is a named customer — CEO Jensen Huang is quoted on CodeRabbit's own site saying "We're using CodeRabbit all over NVIDIA" — alongside other named customers Mastra, Langflow, Clerk, TaskRabbit, Swiggy and Visma.

| Fact | Value |
| --- | --- |
| Website | https://www.coderabbit.ai |
| Pricing | Free for unlimited public/private-repo PR summaries and IDE/CLI review, with a 14-day trial of Pro Plus included; paid per-seat tiers run $24/user/month (Pro) and $48/user/month (Pro Plus, billed annually), with custom-priced Enterprise adding API access, SSO/RBAC and self-hosting. |
| API | Yes |
| Best for | Engineering teams — using a coding agent, or writing code by hand — that want automatic, consistent pull-request review across GitHub, GitLab, Bitbucket or Azure DevOps before a human reviewer looks at it. |
| Not for | Teams looking for an agent that autonomously writes new features or fixes bugs end to end — CodeRabbit's core product reviews code that already exists rather than generating it from a prompt (its Slack Agent add-on and autofix features do generate some code, but review is the primary product). |

## Verdict

CodeRabbit occupies a genuinely different slot in this category than any other listing: it reviews pull requests and commits automatically rather than writing code from a prompt, so it complements a coding agent instead of competing with it. The free tier is real (unlimited repos for PR summaries and IDE/CLI review, not just a capped trial), the funding and NVIDIA reference customer are independently corroborated, and its four-host coverage (GitHub, GitLab, Bitbucket, Azure DevOps) is broader than most single-purpose review tools. The real costs show up going deeper: API access and self-hosting are Enterprise-only, and per-seat paid pricing stacks on top of whatever already generates the code being reviewed.

## Strengths and weaknesses

- ✓ A genuinely different job than every other coding-agents listing here — automated PR/commit review rather than code generation — so it pairs with a coding agent instead of replacing one.
- ✓ Widest code-host coverage among reviewed tools: GitHub, GitLab, Bitbucket and Azure DevOps, plus VS Code/Cursor/Windsurf IDE and CLI review.
- ✓ Real, independently-corroborated funding and a credible enterprise reference: a $60M Series B (Sept 2025) led by Scale Venture Partners with Nvidia's NVentures and CRV, at a ~$550M valuation, and NVIDIA's own CEO Jensen Huang publicly quoted using it.
- ✓ A genuine free tier — unlimited public and private repos for PR summaries and IDE/CLI review — not merely a time-capped trial, plus a separate 14-day Pro Plus trial with no credit card required.
- ✓ Strong independent review signal for a young product category: 4.8/5 on G2 across 26 reviews.
- ✗ API access — the main way to pull review data into another system — is gated behind the custom-priced Enterprise tier, not available on Pro or Pro Plus.
- ✗ Priced per seat on top of whatever tool generates the code in the first place ($24-48/user/month) — an added-cost review layer, not a substitute for a coding agent or human engineer.
- ✗ Headline scale figures (15,000+ customers, 6M repositories, 75M defects found, "most installed AI App" on GitHub/GitLab) are vendor-stated marketing claims on CodeRabbit's own site, not independently audited.
- ✗ Self-hosting and SSO/RBAC — often required for regulated enterprises — sit entirely behind the sales-gated Enterprise tier, the same pattern as much of this category.
- ⚠ G2 reviewers note it can generate comments they consider unnecessary or low-value, adding triage overhead rather than pure time savings.

## Key features

- **Automatic PR review across 4 code hosts** — Reviews pull requests on GitHub, GitLab, Bitbucket and Azure DevOps — broader host coverage than most single-purpose review tools in this category.
- **IDE and CLI pre-commit review** — Reviews code directly in VS Code, Cursor or Windsurf, or via CLI, before a commit is even pushed — not just after a PR is opened.
- **Autofix and advanced finishing touches** — Proposes or applies concrete fixes, generates unit tests, simplifies suggested diffs, and resolves merge conflicts — beyond leaving comments alone.
- **Agentic review chat** — A conversational interface lets a developer question or push back on any specific review comment.
- **Multi-model orchestration** — Combines Claude (Opus/Sonnet/Haiku) and OpenAI models internally, matching model to task complexity rather than exposing one general-purpose model.

## Use cases

- **Automated first-pass review on every PR** — A team wires CodeRabbit into GitHub or GitLab so every pull request — whether written by a human or another coding agent — gets an automatic summary, line comments and bug/security flags before a human reviewer looks at it.
- **Pre-commit review in the editor** — A developer runs CodeRabbit's VS Code, Cursor or Windsurf integration to catch issues before ever opening a pull request.
- **Reviewing AI-generated code specifically** — A team that already uses a code-writing agent (Cursor, Claude Code, Devin) adds CodeRabbit as an independent, automatic reviewer of that agent's output rather than relying solely on human review.

## Integrations

GitHub · GitLab · Bitbucket · Azure DevOps · Jira · Linear · VS Code · Cursor · Windsurf · Slack (via paid Slack Agent add-on)

## Sources

- https://www.coderabbit.ai/
- https://www.coderabbit.ai/pricing
- https://finance.yahoo.com/news/coderabbit-raises-60m-series-b-130000720.html
- https://www.g2.com/products/coderabbit/reviews
- https://claude.com/blog/how-coderabbit-used-claude-to-build-an-agent-orchestration-system
- https://openai.com/index/coderabbit/