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: 90.9%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 148 | 59.7% |
| Cursor Agent | Anysphere | 9 | 3.6% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
9b84b361Localize the last hardcoded UI strings; wire up two dead translations (#16Claude Code5c4b814cLocalize CommandProcessor: all 48 command strings, 30 locales (#1657)Claude Codeeca14719Add 26 code-referenced keys to the catalog + a test that closes the gap (#Claude Code1f59e814Keyboard navigation for @-mention suggestions (#1542)Cursor Agent01523445feat: verification seal on private message sender rows (#1573)Cursor Agent681c1800feat: share location channel invites via the system share sheet (#1513)Cursor Agent
What was excluded
| Commits in window | 257 |
| Merge commits removed | −9 |
| CI / dependency bots removed | −0 |
| Considered | 248 |
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 permissionlesstech/bitchat