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: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Cursor Agent | Anysphere | 12 | 33.3% |
| GitHub Copilot | GitHub | 4 | 11.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
a3822511docs: 新增 5 篇模型动态文章,刷新各家模型最新版本信息Cursor Agent539082c1docs: 新增 6 篇文章,新建大厂官方经验目录,课程链接迁移到 AI 导航Cursor Agent64dccf5cdocs: 在 LICENSE 顶部补充双协议适用范围说明Cursor Agente2aad545Complete all remaining truncated EN translationsGitHub Copilotcfd55d4fFix 38 truncated pre-existing zh-TW translation filesGitHub Copilot3330719dAdd English translations for all missing Vibe Coding tutorial articlesGitHub Copilot
What was excluded
| Commits in window | 208 |
| Merge commits removed | −4 |
| CI / dependency bots removed | −168 |
| Considered | 36 |
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 liyupi/ai-guide