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: 42.9%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 92 | 17.8% |
| GitHub Copilot | GitHub | 14 | 2.7% |
| Cursor Agent | Anysphere | 7 | 1.4% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
8c03fed0test: prune redundant and dead Playwright e2e tests (#13858)Claude Code7e839990Add Hugging Face bucket storage to run history (#13763)Claude Code4eafc18cFix file URLs and sanitize invalid uploaded filenames (#13779)Claude Code55241c89workflow: auto add node on port click (#13557)GitHub Copilotf7b872e5Replace deprecated Starlette 422 status constant in queue validator error GitHub Copilotd4d340d1Provide API endpoint for Workflow graph (actually an endpoint for each subGitHub Copilot8f6f2926Fix SSR apps hanging on Ctrl+C at "Stopping Node.js server..." (#13699)Cursor Agent95369a3dFix Windows filename/path handling (reserved names, node probe, file URLs)Cursor Agent3b12faa4Keep in-flight events working when an app is hot-reloaded (#13627)Cursor Agent
What was excluded
| Commits in window | 521 |
| Merge commits removed | −4 |
| CI / dependency bots removed | −0 |
| Considered | 517 |
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 gradio-app/gradio