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: 19%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 40 | 13% |
| Cursor Agent | Anysphere | 7 | 2.3% |
| GitHub Copilot | GitHub | 2 | 0.7% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
23652c54release(langgraph): 1.2.8 (#8292)Claude Coded2f97191chore(deps): bump redis in /libs/langgraph (#7976)Claude Code2b1abc80chore: migrate Python type checking to ty (#8002)Claude Code95af6a00release(langgraph): 1.2.9 (#8316)Cursor Agentd57a74f9fix: updateState bug for deltaChannel on empty thread (#8011)Cursor Agent6dade64achore: remove unnecessary missing-typed-dict-key suppression (#7744)Cursor Agent4a5765ddrelease: alpha for timers (#7647)GitHub Copilot800071d0chore: idle timeout (#7631)GitHub Copilot
What was excluded
| Commits in window | 577 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −270 |
| Considered | 307 |
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 langchain-ai/langgraph