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: 27.1%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 299 | 6% |
| Cursor Agent | Anysphere | 277 | 5.6% |
| GitHub Copilot | GitHub | 243 | 4.9% |
| OpenAI Codex | OpenAI | 11 | 0.2% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
e4ee6b12M6: document the skills CLI in AGENTS.mdClaude Codeec5328e7M6: deprecation banner on storybook ai setupClaude Code25763ff2M6: fix skills get cwd resolution and clean up config-load errorsClaude Codec676d224Drop the runtime MCP object-schema guard.Cursor Agentb6c178b2Contain change-detection startup failures so stories.changed stays typed.Cursor Agent67755b7bStart module-graph hosting from the first graph query, not CLI bootstrap.Cursor Agent61623259Potential 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 | 7,073 |
| Merge commits removed | −2,076 |
| CI / dependency bots removed | −26 |
| Considered | 4,971 |
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