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: 17.4%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 69 | 5.5% |
| OpenAI Codex | OpenAI | 10 | 0.8% |
| GitHub Copilot | GitHub | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
a2a02424ci: use perf for CodSpeed walltime benchmarks (#21055)Claude Codec6e19ef8Add docker integration test for Windows NanoServer entrypoint installationClaude Codef70693a4Fix inclusion of extra specified in dependency group when listed in a confClaude Code9b58a2e4Support `--require-hashes` in `requirements.txt files` (#19336)OpenAI Codexb4d32e43Vendor packse scenarios and serve them from an in-memory index (#18084)OpenAI Codex78d8fe93Refactor hint handling (#18090)OpenAI Codex726047a4Sync latest Python releases (#19268)GitHub Copilot
What was excluded
| Commits in window | 1,831 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −568 |
| Considered | 1,263 |
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 astral-sh/uv