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: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 221 | 63.3% |
| Cursor Agent | Anysphere | 19 | 5.4% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
037663b5fix(sortable): respect `transition: null` in framework bindingsClaude Codeaa53b823docs: fix incorrect API claims and broken examples across docsClaude Codebdfb1db2docs(changelog): add v0.5.0 release notes and correct release datesClaude Code8e3e5ee5fix: defer flushSync in useDeepSignal to avoid React lifecycle violationCursor Agentcde61e4bfix: batch entity id changes to prevent collision oscillationCursor Agenta774c5fctest: add transformed sortable stories and e2e testsCursor Agent
What was excluded
| Commits in window | 448 |
| Merge commits removed | −93 |
| CI / dependency bots removed | −6 |
| Considered | 349 |
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 clauderic/dnd-kit