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
| Claude Code | Anthropic | 456 | 30% |
| GitHub Copilot | GitHub | 12 | 0.8% |
| OpenAI Codex | OpenAI | 4 | 0.3% |
| Cursor Agent | Anysphere | 2 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
14dd8cfddocs(sandbox): drop the unreleased notice from the OSWorld on Fleet guide Claude Codedb8ba214feat(sandbox): OSWorld disks on Fleet via agent_type="osworld" + "Run OSWoClaude Code4bc38a79docs: align README with current product paths and tutorials (#3649)Claude Codef3e1f8b3Fleet dynamic service exposure: allow PATCH on sandbox services (#7553)GitHub Copilot69ed1112feat(cyclops): require card or admin for CR creation (#6796)GitHub Copilot1532830dfix(cua-driver): hide policy-disabled MCP tools (#3132)GitHub Copilotbec30867feat(cyclops-cs): add GitHub OIDC trust policies (#5249)OpenAI Codexa2c130b6fix(cyclops-cs): classify canceled svc proxy requests separately (#5935)OpenAI Codex8d2ac5eefeat(python): add cua-cloud placeholder package (#2042)OpenAI Codex9c929313Clarify that click already glides the agent cursor overlay. (#3143)Cursor Agenta375b3fffeat(lume): add additional virtio-blk data disksCursor Agent
What was excluded
| Commits in window | 2,007 |
| Merge commits removed | −37 |
| CI / dependency bots removed | −452 |
| Considered | 1,518 |
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 trycua/cua