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: 78.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 193 | 45.5% |
| Cursor Agent | Anysphere | 2 | 0.5% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
3b74643ffix(cli): wait for a freshly started proxy's run state before judging its Claude Codef9a039a9chore(release): cut v2.5.0 and @caveman-ai/cli 1.3.2 on the bin-v1.1.5 runClaude Code14b1c15ffix(cli): fail closed on unverifiable proxy owners, strip attributed routeClaude Code1b7ff8fafix(proxy): scope repo intelligence to project source and require direct eCursor Agent902eba34fix: opencode .jsonc config, plugin agent discovery, shrink nested descripCursor Agent
What was excluded
| Commits in window | 518 |
| Merge commits removed | −75 |
| CI / dependency bots removed | −19 |
| Considered | 424 |
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 JuliusBrussee/caveman