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: 7%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 18 | 4.1% |
| OpenAI Codex | OpenAI | 2 | 0.5% |
| GitHub Copilot | GitHub | 2 | 0.5% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
224fcadbfix: route $derived teardown errors through invoke_error_boundary (#18486)Claude Code2d2e5df2fix: don't turn component instances stored in $state into state proxies (#Claude Code950e2a83fix: strip comments from inline style values in linear time (#18553)Claude Code7719a74echore: fix constructor typo in attributes comment (#18115)OpenAI Codex48dc9b40docs: fix spacing around option tag in bind docs (#18114)OpenAI Codex206974a5chore: generate markdown tables of CPU profiles (#18059)GitHub Copilotdd9fc0d1Warn on non-destructured `$props()` reads in runes mode (#17708)GitHub Copilot
What was excluded
| Commits in window | 499 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −65 |
| Considered | 434 |
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 sveltejs/svelte