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: 10.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Cursor Agent | Anysphere | 102 | 2.3% |
| Claude Code | Anthropic | 42 | 1% |
| GitHub Copilot | GitHub | 4 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
52439937fix(app): make the OpenWork mark interior transparent (#4873)Cursor Agent3b251c66fix(landing): left-align the desktop nav links next to the logo (#4860)Cursor Agentccb9d89efeat(landing): set Work in the body face and keep the dither clear of the Cursor Agente62d0189fix(den): generate ids for oauthResource seeds and disable per-client resoClaude Codeb716d690fix(den): seed MCP resources into the better-auth 1.7 resource registry (#Claude Codeeb4e2251fix(ci): unbreak Den DB Migrate against pscale CLI v0.311+ (#3606)Claude Code66cf3e3dtest: pre-merge regression witnesses + repair the local desktop E2E lane (GitHub Copilot88cbb9f9feat(app): render Mermaid diagrams safely (#4171)GitHub Copilot1fecabf8fix(markdown): render LaTeX math in chat with KaTeX (#3409)GitHub Copilot
What was excluded
| Commits in window | 4,789 |
| Merge commits removed | −55 |
| CI / dependency bots removed | −314 |
| Considered | 4,420 |
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 different-ai/openwork