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: 96.9%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 301 | 58.8% |
| OpenAI Codex | OpenAI | 13 | 2.5% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
8a2fd112feat(wall): keep the admin unlock until explicitly lockedClaude Code24f69433fix(website): point lockfile at the public npm registryClaude Code3490b050docs(agents): 新增 community-pr-loop skill — 社区 PR 处理回路Claude Code555ca9d6fix(buttons): polish open target feedbackOpenAI Codex249835c9feat(buttons): wire OpenTargetConfigPopover end-to-endOpenAI Codex25ea9529feat(buttons): NSOpenPanel + drag-drop file selectionOpenAI Codex
What was excluded
| Commits in window | 534 |
| Merge commits removed | −16 |
| CI / dependency bots removed | −6 |
| Considered | 512 |
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 Caldis/Mos