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: 11.1%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 10 | 3.8% |
| GitHub Copilot | GitHub | 5 | 1.9% |
| Cursor Agent | Anysphere | 1 | 0.4% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
553ef241feat(desktop): suppress the dock while Brain is the topmost window (#7267)Claude Codea04e0eb5feat(desktop): route Stripe returns to declared app (#7208)Claude Code91fa34cafeat(dbprovider): dataflow support (#6925)Claude Code95c027dbfix(resources): bind monitor lifecycle to manager leadership (#7315)GitHub Copilot30669519fix(account): close payment watches and await worker shutdown (#7304)GitHub Copilot15ad047bfix(stargz): annotate injected runtime pods (#84) (#7144)GitHub Copilot9fedc50cfeat(webhooks): add stargz runtime injector webhook (#7042)Cursor Agent
What was excluded
| Commits in window | 263 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 263 |
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 labring/sealos