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: 50.2%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 203 | 29% |
| Cursor Agent | Anysphere | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
2498195adocs(changelog): add v6.12.0 entry and sync marketplace.json (#2824)Claude Codebd7ee167docs(security): add email channel and define the framework security model Claude Code3aa110dffix(customization): resolve the project root from the working directory (#Claude Codeb3d79436docs(zh-cn): add missing translations for forge-idea, web-bundles, and devCursor Agent
What was excluded
| Commits in window | 819 |
| Merge commits removed | −103 |
| CI / dependency bots removed | −15 |
| Considered | 701 |
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