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: 40%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 170 | 6% |
| OpenAI Codex | OpenAI | 1 | 0% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
f8b7f5f7[codex] planning-gate coherence follow-up (#3003)Claude Codeeae4b398refactor(planning-guard): compact #2997/#2998 helpers (no behavior change)Claude Code72f597f4fix(cli): tolerate dead leader pane in detached history prune hook (#2805)Claude Codea33ba7cfTighten root prompt contracts with explicit safety and workflow rationale OpenAI Codex
What was excluded
| Commits in window | 3,846 |
| Merge commits removed | −968 |
| CI / dependency bots removed | −62 |
| Considered | 2,816 |
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 Yeachan-Heo/oh-my-codex