One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
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: 15.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Cursor Agent | Anysphere | 21 | 1.9% |
| Claude Code | Anthropic | 8 | 0.7% |
| GitHub Copilot | GitHub | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
cf692087Display featured fonts inline in Font settings instead of a modal overlay.Cursor Agent41055544Lazy-load font previews in Font settings instead of preloading all fonts iCursor Agentc1334e9cAdd font preview overlay with app and reader font assignment in Font settiCursor Agent10648518feat(supportDialog): 试用到期退出专业版改为直接退出Claude Codea0b68136docs: 添加 CLAUDE.md 项目架构与开发规范文档Claude Code8e3f7f30fix(navigation): reset collapsedChapters on new search and cancelClaude Codead555de9Apply suggestions from code reviewGitHub Copilot
What was excluded
| Commits in window | 1,162 |
| Merge commits removed | −28 |
| CI / dependency bots removed | −0 |
| Considered | 1,134 |
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 koodo-reader/koodo-reader