One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
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: 98.4%. Bars are scaled to that peak, not to 100%.
Which agents
| OpenAI Codex | OpenAI | 643 | 63.6% |
| Claude Code | Anthropic | 217 | 21.5% |
| GitHub Copilot | GitHub | 22 | 2.2% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
792b18c3a2a: configure network-specific NAT64 prefixes (#4924)OpenAI Codex89e2e80edocs: keep only Atlas Cloud sponsor logo (#4922)OpenAI Codex93f6e501docs: remove Anthropic sponsorship (#4921)OpenAI Codex7be97343ai/atlascloud: report token usage from Generate (#4906)Claude Code61729e12agent: let a caller observe run events as they happen (#4905)Claude Code24529f14ci(release): roll CHANGELOG [Unreleased] into the version on tag (#4904)Claude Code24529f14ci(release): roll CHANGELOG [Unreleased] into the version on tag (#4904)GitHub Copilotbd782e28docs(changelog): record the provider tool-loop, caching, and discovery fixGitHub Copilotf31a7acffix: gofmt formatting in ai/anthropic/anthropic.go (#3299)GitHub Copilot
What was excluded
| Commits in window | 1,011 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 1,011 |
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 micro/go-micro