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: 52.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 497 | 19.4% |
| GitHub Copilot | GitHub | 21 | 0.8% |
| Cursor Agent | Anysphere | 2 | 0.1% |
| OpenAI Codex | OpenAI | 1 | 0% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
f18fa025docs(upgrade): document event attributes, signal widening, testing and devClaude Code7ff29627chore: satisfy the dedupe and prettier gatesClaude Codea147c1a1fix(docs): import rolldown's oxc from a browser-reachable subpathClaude Code897027abRefresh deduped pnpm lockfileGitHub Copilot86c4df35fixupGitHub Copilota8eb1b61Prevent inline qwikloader emission inside SVG/MathML foreign content in v2GitHub Copilot839be6a8docs(state): refresh post PR #244 merged — OSS-481 Done; NAPI-parity creatCursor Agentd3e3b8c1feat(OSS-481): true NAPI parity for createOptimizer — raw-string boundary,Cursor Agent7d9124e9fix: wrapper function naming for bare $() + smarter AST raw field strippinOpenAI Codex
What was excluded
| Commits in window | 3,209 |
| Merge commits removed | −500 |
| CI / dependency bots removed | −145 |
| Considered | 2,564 |
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 QwikDev/qwik