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: 5.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 17 | 1.6% |
| GitHub Copilot | GitHub | 3 | 0.3% |
| Cursor Agent | Anysphere | 2 | 0.2% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
7a298c99fix(headers): anchor SameSite value regex (#11615)Claude Code9ed06e63Optimize UI runtime hot paths and fix benchmark runner measurement (#11613Claude Coded1508263Rework css mixin style ownership into a pinned global registry (#11612)Claude Code52c31c62Add Pagefind search to prerendered docs (#11461)GitHub Copilot3fb9542dAdd dark mode to docs site (#11415)GitHub Copilot1ca78b0dAdd UI component demos to the docs site (#11397)GitHub Copilot06956015ryan/multipart perf (#11083)Cursor Agentfc6ff900refactor(data-table): add high-level db.count helperCursor Agent
What was excluded
| Commits in window | 1,052 |
| Merge commits removed | −3 |
| CI / dependency bots removed | −0 |
| Considered | 1,049 |
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 remix-run/remix