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: 26.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 31 | 8.2% |
| Cursor Agent | Anysphere | 3 | 0.8% |
| OpenAI Codex | OpenAI | 1 | 0.3% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
b6da5227[DOM] Stop emulating bubbling for toggle and beforetoggle events (#37580)Claude Code564923c8[DOM] Add support for `onAnimationCancel` (#37609)Claude Code084f5f24[ci] Compare size against merge base (#37355)Claude Code019019be[DOM] Fix Fragment compareDocumentPosition(document) TypeError (#37579)Cursor Agent0209ef8a[DevTools] Fix reconciliation of content with fallback Fiber (#37475)Cursor Agent5a90a5a7[compiler] Bail out with Todo on using and await using declarations (#3694Cursor Agent6e9c55c3perf(compiler): Check component params before scanning bodies (#37622)OpenAI Codex
What was excluded
| Commits in window | 384 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −4 |
| Considered | 380 |
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 react/react