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: 96.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 583 | 76.5% |
| Cursor Agent | Anysphere | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
8b0fca4afix(book-to-skill): correct emitter docstring drift and the resident-core Claude Code3301348dfix(docs): correct the commands delta and a README spacing nitClaude Code942e7713fix(deep-learning-book): reject overlapping capacity regime bandsClaude Code0898558efix(integrations): update find depth in convert.sh for new repo structureCursor Agent
What was excluded
| Commits in window | 1,330 |
| Merge commits removed | −448 |
| CI / dependency bots removed | −120 |
| Considered | 762 |
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 alirezarezvani/claude-skills