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: 86.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 300 | 58.9% |
| Cursor Agent | Anysphere | 18 | 3.5% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
183c5d8cchore(deps): bump lopdf to 0.45.0 (#534)Claude Code72f7c718feat(positions): add a display frame option to the positioned-text and regClaude Code6e6a71ccfix(loader): rebuild classic xref tables with 19-byte entries (#508)Claude Code4bee4f99chore(release): bump package versions to 1.14.2 (#382)Cursor Agent1719d248fix(tables): bound disjoint-rect clustering so overlap tests stay subquadrCursor Agentf114e79cfix(detector): bound Tj/TJ operand lookback to the previous operator (#380Cursor Agent
What was excluded
| Commits in window | 516 |
| Merge commits removed | −7 |
| CI / dependency bots removed | −0 |
| Considered | 509 |
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 firecrawl/pdf-inspector