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: 22.2%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 377 | 10.6% |
| Cursor Agent | Anysphere | 29 | 0.8% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
55f881f4docs(agent): document the variable tool Permission Mode (#7832)Claude Code95e0607efeat(agent): allow variable tool permission modes (#7538)Claude Codeb2b9eedcfix(tables): use explicit timestamps for expiration (#7689)Claude Code25d8019afeat(pi): Babysit foundations — shared PR/push extraction, five GitHub tooCursor Agente8e3d698feat(pi): optional multi-provider web search for the coding agent (#5951)Cursor Agentd24bc7ecfeat(agent-stream): thinking and tool streaming (#5671)Cursor Agent
What was excluded
| Commits in window | 3,825 |
| Merge commits removed | −257 |
| CI / dependency bots removed | −0 |
| Considered | 3,568 |
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 simstudioai/sim