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: 17.1%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 8 | 2.5% |
| OpenAI Codex | OpenAI | 3 | 0.9% |
| Cursor Agent | Anysphere | 2 | 0.6% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
9375667ffix: prefer known system Python paths over PATH resolution in hook scriptsClaude Code34666a07fix: cap session-catchup output before injecting into model context (#138)Claude Code9f7c0d26fix: correct PowerShell syntax in Pi session-catchup invocation (#137)Claude Code4ffd78cePrefer current Codex thread for catchupOpenAI Codex14ea1099Tighten Codex catchup message parsingOpenAI Codex5df903e0Add Codex session catchup supportOpenAI Codex28e89aaedocs: rename moltbot.md to openclaw.mdCursor Agentcbf393a5docs: update moltbot.md to use OpenClaw naming and pathsCursor Agent
What was excluded
| Commits in window | 346 |
| Merge commits removed | −20 |
| CI / dependency bots removed | −0 |
| Considered | 326 |
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 OthmanAdi/planning-with-files