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: 0.6%. Bars are scaled to that peak, not to 100%.
Which agents
| OpenAI Codex | OpenAI | 7 | 0.1% |
| Claude Code | Anthropic | 5 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
9c77f54eTrail replayed potential throw sitesOpenAI Codex9beb003aAdd regression test for issue 77718OpenAI Codexadba6dfbAdd generic actor coverage to gh87462OpenAI Codex83eb806d[utils] Add an add-worktree utilityClaude Code948d7311[update-checkout][test] Several utils/update_checkout/tests/test_cross_repClaude Codec93aa767Serialization: Don't drop generic type-alias type witness decls cross-moduClaude Code
What was excluded
| Commits in window | 7,630 |
| Merge commits removed | −2,468 |
| CI / dependency bots removed | −0 |
| Considered | 5,162 |
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 swiftlang/swift