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: 18.2%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 7 | 4% |
| GitHub Copilot | GitHub | 2 | 1.2% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
25f60fff【安全修复 GHSA-4c6j-45p9-rhrw】填值规则管理接口缺少权限校验Claude Code34191cde【安全修复 GHSA-7wcq-939v-pcrg】字典翻译切面绕过序列化注解导致数据源密码泄露Claude Code0941ed6fdocs: README 发布日期改为 2026-04-30Claude Code24338e56fix(docker): 单体前端nginx改用docker内嵌DNS运行时解析后端地址GitHub Copilot37a5e684升级 minio 到 9.0.3，适配 Method 类迁移及 stream 方法签名变更GitHub Copilot
What was excluded
| Commits in window | 184 |
| Merge commits removed | −11 |
| CI / dependency bots removed | −0 |
| Considered | 173 |
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 jeecgboot/JeecgBoot