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: 28%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 21 | 2.7% |
| Cursor Agent | Anysphere | 4 | 0.5% |
| GitHub Copilot | GitHub | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
b6d82c6ffix: apply global font size to summary message content (#681)Claude Codec83dfff0fix: resolve Anthropic OAuth API invalid_request_error (#680)Claude Code63f9eaebchore: configure pnpm minimumReleaseAge for supply chain security (#673)Claude Code0b8a3c95release 1.23.1Cursor Agent2b46d9d0docs: add v1.23.1 user-facing changelogCursor Agentc953f5eftest: adapt memory reload harness to release-1.23 storageCursor Agentd8545b3afix: only new message on top (#665)GitHub Copilot
What was excluded
| Commits in window | 772 |
| Merge commits removed | −1 |
| CI / dependency bots removed | −0 |
| Considered | 771 |
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 chatboxai/chatbox