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: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Cursor Agent | Anysphere | 8 | 9.3% |
| Claude Code | Anthropic | 2 | 2.3% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
81817aedci: remove the deadsnakes job (#6052)Cursor Agent9cc298a4ci: pass explicit ARM64 Python artifacts on windows-11-arm (#6051)Cursor Agentc5b3ae81ci: pin PyPy 3.11 to 7.3.21 on macOS and Windows (#6050)Cursor Agent46ebf503feat(subinterpreter): reusable PyThreadState via subinterpreter_thread_staClaude Codee7754de0Revert internals destruction and add test for internals recreation (#5972)Claude Code
What was excluded
| Commits in window | 106 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −20 |
| Considered | 86 |
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 pybind/pybind11