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: 6%. Bars are scaled to that peak, not to 100%.
Which agents
| Cursor Agent | Anysphere | 86 | 1.7% |
| Claude Code | Anthropic | 48 | 0.9% |
| OpenAI Codex | OpenAI | 3 | 0.1% |
| Devin | Cognition | 1 | 0% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
45889198fix(agent): decouple read coverage from write evidence recoveryCursor Agent99040648fix(desktop): gray out locked provider name with a rename hint / 灰显供应商名称并提Cursor Agentf53edb59fix(session): fold recovery lineages into one ordinary list row / 恢复谱系折叠为单Cursor Agentc9efeec8fix(desktop): build Windows service as GUI subsystemClaude Code36d418e6feat(serve,desktop): multi-session detach, gzip snapshot transport, and crClaude Code7d88bbe8docs(boot): restore applyUnifiedProviderToolSurface's doc commentClaude Code1a87cd4cIntegrate clear context telemetry fixes / 集成清空上下文与统计面板修复 (#4329)OpenAI Codex368dad0efix(desktop): honor user font in UI chrome (#3605)OpenAI Codexf6e6673dfeat(desktop): add text size shortcuts (#3576)OpenAI Codexf8758bb5fix(desktop): persist the restore rectangle instead of the maximized frameDevin
What was excluded
| Commits in window | 7,082 |
| Merge commits removed | −1,780 |
| CI / dependency bots removed | −119 |
| Considered | 5,183 |
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 esengine/DeepSeek-Reasonix