One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
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: 50%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 207 | 11.6% |
| Claude Code | Anthropic | 23 | 1.3% |
| Cursor Agent | Anysphere | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
a31f9e52Refactor kitty_tests: move __init__.py code to base.py, update all importsGitHub Copilota36b259dFix parser to strip semicolons from module/import names; update testsGitHub Copilotd8041066Add slang parser corner case tests and implement test_slang_orderingGitHub Copilot8b564c70Go shlex: Do not drop empty quoted stringsClaude Code0791b39aFix completion after a trailing space in the kitty shellClaude Code2dbe5df2Wayland: fix crash when an output global is removedClaude Code98366076fix(wayland): detect start_drag silently ignored by the compositorCursor Agent
What was excluded
| Commits in window | 2,137 |
| Merge commits removed | −310 |
| CI / dependency bots removed | −48 |
| Considered | 1,779 |
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 kovidgoyal/kitty