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: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 63 | 15.4% |
| Cursor Agent | Anysphere | 3 | 0.7% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
b36e0829Release v6.3.0: Devin CLI and Hermes Agent support, brainstorming three-paClaude Code28b96af9chore(codex): remove orphaned session-start-codex hook + refresh hook docsClaude Code7d8d3d4bfix(codex): suppress SessionStart hook auto-discovery with empty hooks objClaude Codeb36e0829Release v6.3.0: Devin CLI and Hermes Agent support, brainstorming three-paCursor Agent6015d37ffix(systematic-debugging): match find -path ./ prefix in find-polluter.sh Cursor Agent772ec9f8Add Cursor plugin manifest and hook response compatibilityCursor Agent
What was excluded
| Commits in window | 427 |
| Merge commits removed | −18 |
| CI / dependency bots removed | −0 |
| Considered | 409 |
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 obra/superpowers