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: 6.5%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 4 | 1.4% |
| Claude Code | Anthropic | 3 | 1.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
d061c263fix(remove): unwrap single sequence expression (#18183)GitHub Copilot25f2e4a3fix: improve inputSourceMap URL handling (#17999)GitHub Copilotf297c423Add testing for plugin options (#17957)GitHub Copilot6684fa3fchore: bump lru-cache to v11 and drop @types/lru-cache (#18038)Claude Codeb79f64a1chore: update cipher-base (#17979)Claude Codef5de931aFix TypeScript parser failing on async calls in ternary consequent (#17799Claude Code
What was excluded
| Commits in window | 284 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −1 |
| Considered | 283 |
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 babel/babel