← the index
DIYgod/RSSHub
5.9%
of 612 commits were committed by an AI agent — a floor, not an estimate
5.9% agent · top contributor 16.7%21 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

36
agent commits
576
human commits
21
agent contributors
16.7%
largest contributor

Assisted or autonomous

34assisted
2autonomous

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

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 8%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic284.6%
GitHub CopilotGitHub71.1%
Cursor AgentAnysphere10.2%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • 10ed0dbffix(route): dedupe lg/tokyo/food-permit by 許可番号Claude Code
  • 5262341afeat(route): add lg/osaka/food-permitClaude Code
  • 75c58624feat(route): lg/tokyo/food-permit adds 目黒区 飲食店 新規 monthly CSVClaude Code
  • d4a2bb48chore(deps-dev): bump pnpm from 10.34.4 to 10.34.5 (#22748)GitHub Copilot
  • 42c6d097chore(deps): bump tsx from 4.23.0 to 4.23.1 (#22700)GitHub Copilot
  • 0b2b8e0efeat(route/qwen): replace deprecated qwen blog route with new one (#21944)GitHub Copilot
  • cae03809fix(route/patreon): creator ID extraction and render content from JSON (#2Cursor Agent

What was excluded

Commits in window1,789
Merge commits removed0
CI / dependency bots removed1,177
Considered612

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 DIYgod/RSSHub

Scan another repository