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: 85.2%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 4039 | 49.7% |
| Cursor Agent | Anysphere | 19 | 0.2% |
| GitHub Copilot | GitHub | 1 | 0% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
4e55cdcafix(meetings): make the replay progress bar seekable and stop blanking padClaude Codeb5cc23e0fix(chat): stop empty "untitled" chats appearing in recents (#6667)Claude Code5f0b135ffix(acp): keep Codex skills-budget warnings out of the chat transcript (#6Claude Code7fdb4aa6feat(chat): archive the current tab with Cmd+E (#6752)Cursor Agent62fd6faefix(chat): render local markdown images outside the asset protocol (#6751)Cursor Agent4590b14afix(chat): put conversation actions on the tab (#6748)Cursor Agenta3f0b368chore: add .claude/*.local* to gitignore (#2342)GitHub Copilot
What was excluded
| Commits in window | 8,491 |
| Merge commits removed | −280 |
| CI / dependency bots removed | −79 |
| Considered | 8,132 |
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 screenpipe/screenpipe