- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
A Git extension for tracking the AI-generated code in your repos
01Result
git-ai-project/git-ai ↗git-ai-project/git-ai AI coding statistics: 58.7%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.
Agent share by month
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-01 | 0% | 2 |
| 2026-02 | 44.5% | 479 |
| 2026-03 | 46.7% | 492 |
| 2026-04 | 74.6% | 508 |
| 2026-05 | 82.4% | 505 |
| 2026-06 | 52.8% | 576 |
| 2026-07 | 17.4% | 161 |
| 2026-08 | 53.7% | 121 |
| 2026-09 | 100% | 80 |
Peak month: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 1459 | 49.9% |
| Devin | Cognition | 217 | 7.4% |
| GitHub Copilot | GitHub | 25 | 0.9% |
| Cursor Agent | Anysphere | 12 | 0.4% |
| OpenAI Codex | OpenAI | 4 | 0.1% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
6adc1f26on GitHubperf(api): cache git author identity resolution with a 30-minute TTLClaude Code92a89746on GitHubfix(usage): keep straddling and cost-only token bucketsClaude Codec555675eon GitHubfeat(usage): source tokens and cost from TokenUsage events exclusivelyClaude Code9259bd4bon GitHubfix(ci): migrate Slack notify step to slack-github-action v4 APIDevin111a9132on GitHubUpdate .github/workflows/coverage.ymlDevin143915dcon GitHubUpdate .github/workflows/performance-benchmarks.ymlDevin92ccd900on GitHubAdd Discord badge to READMEGitHub Copilot2e410951on GitHubInitial planGitHub Copilot719971f2on GitHubClarify NTSTATUS docsGitHub Copilot53a5b751on GitHubfix(visualstudio): capture content at event time and clean up before-edit Cursor Agent02c27de9on GitHubfix(visualstudio): fix ineffective process timeout in BinaryResolverCursor Agent5170243aon GitHubfix(visualstudio): address PR review commentsCursor Agent90553fa7on GitHubLimit daemon log field payloadsOpenAI Codexa7eae616on GitHubFix daemon log retry buffer orderingOpenAI Codex08ecd022on GitHubAdd daemon log upload clientOpenAI Codex
04Method
What entered the denominator
The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.
Exclusion ledger
| Commits in window | 4,043 |
| Merge commits removed | −817 |
| CI / dependency bots removed | −302 |
| Considered | 2,924 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
Run the same detector locally.
Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.
npx qmmit-cli git-ai-project/git-ai