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: 5.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 5 | 0.5% |
| Cursor Agent | Anysphere | 2 | 0.2% |
| GitHub Copilot | GitHub | 2 | 0.2% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
0e55ffceRequire operator, not agent, to write PR descriptionsClaude Code73644203Avoid ninja schema cache collisions across different base_class callsClaude Code6a104efdHandle swappable Page model correctly in legacy data migrationsClaude Code775873a2Add filtering to the API token admin list viewCursor Agentc7890985Rename API token admin module paths to api_tokensCursor Agent0adefef7Add "Maintenance task" GitHub issue template (#14282)GitHub Copilotd8b53811Rework "Using the picture element" docs to showcase the `{% picture %}` taGitHub Copilot
What was excluded
| Commits in window | 1,005 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −58 |
| Considered | 947 |
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 wagtail/wagtail