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: 49.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 206 | 24.6% |
| Cursor Agent | Anysphere | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
696cef51docs(diagrams): let the delivery loop's two slogans carry the accent (#285Claude Code116e703ddocs: refresh the README banner, restore its diagram, and fix the favicon Claude Code42de7ff1fix(docs-site): act on the review findings from #2850 (#2851)Claude Codeb3d79436docs(zh-cn): add missing translations for forge-idea, web-bundles, and devCursor Agent
What was excluded
| Commits in window | 955 |
| Merge commits removed | −104 |
| CI / dependency bots removed | −15 |
| Considered | 836 |
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 bmad-code-org/BMAD-METHOD