CodeRabbit
Code-review agent for pull requests and local changes, with suggested fixes, agent-authored code-change PRs, and review loops that integrate with coding agents.
Attributed output
GitHub public-attribution count, 2026-10-12
22.6K PRsAttributed outputGitHub public-attribution count, 2026-10-12Commits and PRs on public GitHub provably produced by this agent. Exact if it is visible through its own bot or workflow, an estimate if measured through attribution it declares (these can swing 30 to 40 percent between measurement runs at multi-million scale), and a floor either way.Index rank · all agents
#7 of 40 CLI agents
#8Index rank · all agents#7 of 40 CLI agentsRanked by agent-opened PRs in the trailing 4 complete weeks, matching the index. Agents without a tracked PR series follow, ordered by total attributed output. Other filters or sorts change the list position.n/a
Business signal
No sourced business metric
n/aBusiness signalNo sourced business metricFree tier; paid from $30/mo
Entry price
Developer subscription
Free tier; paid from $30/moEntry priceDeveloper subscriptionNot published
GitHub stars
No public repo
Not publishedGitHub starsNo public repoNot published
npm demand/wk
Public npm counter
Not publishednpm demand/wkPublic npm counterWeekly package downloads as an install-demand floor; adjusted when the vendor's main install channel is no longer npm.From the public record
6,544 PRs · 2,468 repositories
Search window: – · captured Oct 13, 2026 (UTC)
15.6%81 / 519 auto-fix PRs
81 of 519 auto-fix PRs followed work crediting Claude, Cursor, Codex, Devin, Copilot Autofix or Jules. They trace to 74 original PRs across 60 repositories. 57 of the 81 follow-ups were merged (70.4%). This is a confirmed subset, not the share of all CodeRabbit work involving other agents.
25.6%1,672 / 6,544 audited PRs
1,672 PR descriptions explicitly record a chat request to make code changes; 1,095 of those PRs were merged. The public record shows developers using the reviewer to open implementation PRs from existing conversations.
35.7%2,338 / 6,544 audited PRs
1,300 PRs explicitly request unit-test generation and 1,038 request docstrings: 2,338 combined. These classify the requested workflow; individual patches can include other changes.
Public PRs opened by CodeRabbit only; reviews on other authors’ PRs and private work are excluded. Signatures credit assistance, not exclusive authorship or an autonomous workflow. Missing signatures do not mean human-only work. Merged does not establish correctness. GitHub results can change after capture.
Collected every returned public CodeRabbit-bot-authored PR in 20 weekly searches, each below GitHub’s retrieval cap. Validated pagination, unique PR IDs, public repositories and bot identity. Classified explicit workflow markers in titles/descriptions. Traced all 451 original PRs behind the 519 auto-fix follow-ups, inspecting their descriptions and first 10 commit messages for agent attribution. Claude coauthor credits can identify a model without identifying its client. Metadata/descriptions were analyzed throughout; selected code diffs were spot-checked.
Returned records dated May 25, 2026–Oct 11, 2026.
Download the dated audit evidence (JSON)Weekly attributed output on public GitHub. Output visible through the agent's own bot or workflow is exact; output measured through declared attribution is an estimate. Window: 2025-02-03 to 2026-10-05.
Public pull requests opened by CodeRabbit
Pull requests authored by CodeRabbit's own workflow, including fixes and requested code changes. This measures authored PRs, not the much larger set of PRs it reviews, review comments, or all CodeRabbit usage.
Last full week (ending 2026-10-11): 261 agent-marked PRs (-3.7% week over week), exact count.
Merge rate: 70.3% of its pull requests get merged (1,931 of 2,747 over 8 settled weeks, 2026-08-10 to 2026-10-04). The window ends about ten days back so recently-opened PRs have had time to merge.
GitHub review activity: 19% of its merged PRs had at least one GitHub review record before merging; the other 81% had none. This is a broad weekly signal and can include bot reviews; the human-review read below comes from the enriched PR sample.
Snapshot 2026-10-12, confidence High, tracked since 2026-06-09. Read the methodology.
Pricing snapshot: 2026-10-12. Check the vendor for current terms.
Free access; Essentials $30 and Team $60 per developer on monthly billing.
No guaranteed token allocation. Annual billing reduces Essentials to $24 and Team to $48 per month.
| Plan | Price | Allowance | Unit | Token / Overage Notes |
|---|---|---|---|---|
| Free | Free | Limited review access. | Reviews | |
| Essentials | $30/developer/mo | Essentials review features; see current fair-use limits. | Reviews | |
| Team | $60/developer/mo | Team review features and integrations. | Reviews |
Summary checked 2026-10-12.
Free access is available. Essentials is $30/developer/month and Team is $60 on monthly billing; annual billing is discounted.