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: 18.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 62 | 9.9% |
| GitHub Copilot | GitHub | 5 | 0.8% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
98dc6eeffeat(gitops): show Workflow badge on git-backed resources [BE-13391] (#356Claude Code4ecbf4a4refactor(statsview): migrate polling to useQuery [BE-13372] (#3538)Claude Codedae46021fix(gitops): skip the source type selection step [BE-13379] (#3548)Claude Code359b3c5dfix(websocket): set pod exec query params [C9S-353] (#3423)GitHub Copilotb80c6b47fix(kubernetes): Reload admin token for local k8s environments every 30s [GitHub Copilot4c5ec443feat(addons): add rich info to addon details [R8S-1166] (#3241)GitHub Copilot
What was excluded
| Commits in window | 628 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 628 |
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 portainer/portainer