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: 8.3%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 9 | 2.3% |
| OpenAI Codex | OpenAI | 3 | 0.8% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
4716e5f5Improve error message (#19671)GitHub Copilot36bc0b7eImprove error message for lint-change script (#19641)GitHub Copilot314e61a8Potential fixes for 2 code quality findings (#19640)GitHub Copilot24f4220bImprove `>` handling in blockquote in Markdown (#19802)OpenAI Codex560146e6Markdown: Fix liquid flow parsing (#19838)OpenAI Codexbf3ca0c8Markdown: Fix parse error in liquid plugin (#19411)OpenAI Codex
What was excluded
| Commits in window | 750 |
| Merge commits removed | −10 |
| CI / dependency bots removed | −347 |
| Considered | 393 |
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 prettier/prettier