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: 33.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 186 | 26.9% |
| GitHub Copilot | GitHub | 2 | 0.3% |
| Cursor Agent | Anysphere | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
e131914dfix: 对齐官方 2.1.205 compact prompt 的安全加固Claude Code73a07c69fix: 修复 lastCacheSafeParams 跨会话残留导致 post-turn fork 上下文污染Claude Codee09071acfeat: /compact 保留上下文并新增流式 token 进度条Claude Codecf33c060添加deepseek-v4-pro支持选择max思考深度 (#365)GitHub Copilot2da65140feat: 支持自托管的 remote-control-server (#214)GitHub Copilot3e3e1de8feat: /goal命令能力支持，参考codex实现 (#1261)Cursor Agent
What was excluded
| Commits in window | 834 |
| Merge commits removed | −109 |
| CI / dependency bots removed | −34 |
| Considered | 691 |
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 claude-code-best/claude-code