Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
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: 34.1%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 206 | 19% |
| Cursor Agent | Anysphere | 51 | 4.7% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
f31cc7bedocs: document undocumented Cube Cloud features (#11880)Claude Codebb1f4197docs: regenerate API reference for platform-client v0.11.0 (#11882)Claude Codeaf79bfe4fix(tesseract): bound a rolling window's base scan by literals (#11870)Claude Codeab48039ffix(query-orchestrator): initialize missing data source queue in isPartitiCursor Agent13f1c915perf(schema-compiler): optimize granularityHierarchies to avoid O(n^2) objCursor Agent281e9209feat(cubesql): merge view joins on a shared cube member into a single CubeCursor Agent
What was excluded
| Commits in window | 1,144 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −59 |
| Considered | 1,085 |
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 cube-js/cube