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: 13.6%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 7 | 3.1% |
| Cursor Agent | Anysphere | 6 | 2.6% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
aea94352refactor(p2p): improve HTTP client request logging and credential string fGitHub Copilote444bc49fix: avoid panic in user audit event resolver on nil event data (#23461)GitHub Copilotabc41cc9Fix/api completeness (#23476)GitHub Copilot3a949807refactor: sanitize connection details in logs and enhance error message foCursor Agentaea94352refactor(p2p): improve HTTP client request logging and credential string fCursor Agent73cff4d7Remove hardcoded credentials and prevernt passwords in logs (#23835)Cursor Agent
What was excluded
| Commits in window | 260 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −31 |
| Considered | 229 |
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 goharbor/harbor