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: 82.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 173 | 46.9% |
| GitHub Copilot | GitHub | 4 | 1.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
7f0ee556Declare IPython's built-in magics lazilyClaude Code5b8c0bd9Defer IPython.core.oinspect import out of the startup pathClaude Code4b18de34ci: run mypy on Windows, plus cross-platform --platform checksClaude Code7f24f50bUpdate version9.rst: document all IPython 9.10 PRs and add narrative sectiGitHub Copilot2ef68762Fix SQLite ResourceWarning: unclosed database in HistoryAccessor (#15128)GitHub Copilot516b92bcAdd type hints to IPython/utils/openpy.pyGitHub Copilot
What was excluded
| Commits in window | 421 |
| Merge commits removed | −47 |
| CI / dependency bots removed | −5 |
| Considered | 369 |
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 ipython/ipython