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: 3.1%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 7 | 1% |
| Claude Code | Anthropic | 3 | 0.4% |
| Cursor Agent | Anysphere | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
626b63c1feat: feed intelligence sources into analysis contexts (#1709)GitHub Copilot4610dcbbfix: 补齐 Web 设置页中文文案映射并本地下拉选项翻译 (#1453)GitHub Copilot0fca72a9Refactor: isolate MiMo fallback pricing hook and complete #1282 fix (#1350GitHub Copilot8b5056a1fix: parameterize market context in LLM prompts (#644) (#802)Claude Code057036c8fix missing search engine env vars in GitHub Actions (#625)Claude Codea67933e2fix: 修复 ARCH_ARGS 空数组导致的 unbound variable 错误 (#458)Claude Codeee635a35feat: 桌面端右上角增加更新入口 (#2274)Cursor Agent
What was excluded
| Commits in window | 731 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 731 |
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 ZhuLinsen/daily_stock_analysis