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: 37%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 17 | 11.5% |
| OpenAI Codex | OpenAI | 1 | 0.7% |
| Claude Code | Anthropic | 1 | 0.7% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
92443a90fix(solver): resolve conflicts between mutually exclusive markers (#10944)GitHub Copilot967c46d2fix(solver): prune sibling deps disjoint with override marker context (#10GitHub Copilot9be6dd6eavoid spurious empty-constraint conflict with duplicates across extras (#1GitHub Copilotf9a330f3docs: fix SHA wording in git backend comment (#10843)OpenAI Codex1449345afix: pass auth via Request constructor instead of calling HTTPBasicAuth onClaude Code
What was excluded
| Commits in window | 156 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −8 |
| Considered | 148 |
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 python-poetry/poetry