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: 93.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 191 | 70.5% |
| GitHub Copilot | GitHub | 9 | 3.3% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
b32009e8chore: release v2.85.0Claude Code7b9b1c76fix: accept a null output branch and validate Switch rules.values (v2.84.4Claude Code589d562bfix: report malformed connection shapes instead of throwing (v2.84.3) (#10Claude Code29c6ee6cchore: update n8n to 2.29.x (#923)GitHub Copilot46e97153fix: add form-data@^4.0.6 to package.runtime.json runtime dependenciesGitHub Copilotdf997d41fix: sync runtime version (Concieved by Romuald Członkowski - www.aiadvisoGitHub Copilot
What was excluded
| Commits in window | 335 |
| Merge commits removed | −51 |
| CI / dependency bots removed | −13 |
| Considered | 271 |
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 czlonkowski/n8n-mcp