A small group is using agents. Adoption has spread beyond one person but is not project-wide.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.
Agent share by month
Peak month: 90.6%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 987 | 51.6% |
| Cursor Agent | Anysphere | 4 | 0.2% |
| GitHub Copilot | GitHub | 3 | 0.2% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
25393b46test(worker): stop spinning the loop the awaited work needsClaude Codee1127099fix(backend): identify the port holder by the marker header, not a body snClaude Codef21ad9a2fix(crash): close the far end of a dead run's slice, and settle one at a tClaude Code37aea507fix(setup): lengthen HF connectivity probe timeouts to 8sCursor Agent9979f1a8fix(bootstrap): apply China PyPI mirror on repair uv syncCursor Agent9d30774efeat(audiobook): synced lyrics playback (#1766)Cursor Agentc0924f5efix(tts): torch.compile failures fall back to eager — generation never faiGitHub Copilot853b9eeffix(dub): burn translated subtitles, fix subtitle save JSON error (#309) (GitHub Copilot48ae4daefix(dub): re-dub honors transcript edits — fingerprints canonicalised, preGitHub Copilot
What was excluded
| Commits in window | 2,540 |
| Merge commits removed | −613 |
| CI / dependency bots removed | −15 |
| Considered | 1,912 |
Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.
How this was measured
Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.
Run it yourself: npx qmmit-cli debpalash/VoiceStudio