A small group is using agents. Adoption has spread beyond one person but is not project-wide.
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: 9.1%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 3 | 1.6% |
| Cursor Agent | Anysphere | 2 | 1.1% |
| Claude Code | Anthropic | 2 | 1.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
5b67c048feat(core): add `noScope` key determines whether to wrap the selector (#51GitHub Copilot037ba011feat(core): support `*` parse in variant group (#5124)GitHub Copilot20c382acchore: toggle off a lint rule for docs build (#5119)GitHub Copilote74667e8fix(eslint-plugin): sort `unoVariables` class strings wrapped in `satisfieCursor Agentf3e75cf1fix(webpack): filter load/transform hooks away from binary assets (#5275)Cursor Agenta4f4dce2fix(svelte-scoped): handle @property at-rules in writeUtilStyles (#5260)Claude Codebab376e8fix(playground): await prettier when formatting panels (#5256)Claude Code
What was excluded
| Commits in window | 185 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 185 |
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 unocss/unocss