Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
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: 26.9%. Bars are scaled to that peak, not to 100%.
Which agents
| Cursor Agent | Anysphere | 415 | 7% |
| Claude Code | Anthropic | 330 | 5.6% |
| GitHub Copilot | GitHub | 243 | 4.1% |
| OpenAI Codex | OpenAI | 11 | 0.2% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
60f9441eManager: Move timeout-detection removal to a separate PRCursor Agente7f59fc8Manager: Drop client-side server timeout detectionCursor Agentd500a722Manager: Use a valid close code in node-channel testsCursor Agent47f61bf8Add a copy button to the upgrade command snippetClaude Code14bbacbcUse TabList/TabPanel for the upgrade block's package manager tabsClaude Code225e5643Fix focus indicators and Tab stepping in the mobile about overlayClaude Code61623259Potential fix for pull request findingGitHub Copilot82dec992Apply suggestions from code reviewGitHub Copilotfa2691d8Potential fix for pull request findingGitHub Copilot4a76b605Chore: fix eval formattingOpenAI Codexc4a883e4Eval: make baseline MDX consumers safeOpenAI Codex3e26b594Eval: make baseline templates readableOpenAI Codex
What was excluded
| Commits in window | 8,427 |
| Merge commits removed | −2,493 |
| CI / dependency bots removed | −26 |
| Considered | 5,908 |
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 storybookjs/storybook