Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
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: 25%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 19 | 1.6% |
| Cursor Agent | Anysphere | 2 | 0.2% |
| OpenAI Codex | OpenAI | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
0ee59b8dfeat(docs): await asynchronous document creation (#2641)Claude Coded289566afeat(base): require --fields on +table-create (#2221)Claude Code8ba910ebfix(slides): reindent xml-get output for readability (#1987)Claude Code38e8806dfeat: event description support rich text (#1975)Cursor Agent0bf590d0feat: get minutes keywords (#1079)Cursor Agent723f884efeat(base): support BaseApp application mode (#2231)OpenAI Codex
What was excluded
| Commits in window | 1,176 |
| Merge commits removed | −1 |
| CI / dependency bots removed | −9 |
| Considered | 1,166 |
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 larksuite/cli