← the index
vercel/turborepo ↗
8.1%
of 1,262 commits were committed by an AI agent — a floor, not an estimate
8.1% agent · top contributor 71.6%19 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

102
agent commits
1,160
human commits
19
agent contributors
71.6%
largest contributor

Assisted or autonomous

100assisted
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

Peak month: 31.9%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic504%
Cursor AgentAnysphere504%
GitHub CopilotGitHub40.3%

Verify it yourself

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

  • c4ac03b4feat: Add daily performance agent (#13729)Claude Code
  • 6a46551achore: Enforce draft pull requests (#13726)Claude Code
  • aa070b14feat: Notify Slack when agents open PRs (#13722)Claude Code
  • c8eaedc8refactor: Remove residual runtime PackageInfo gates (#13564)Cursor Agent
  • 1bb92331refactor: Remove prune PackageInfo dependencies (#13562)Cursor Agent
  • 4cb9d94erefactor: Migrate MFE dependency detection off PackageInfo (#13558)Cursor Agent
  • c6fbc97bdocs: Explain affected package invalidation reasons (#13594)GitHub Copilot
  • 4a4e661fchore: Update AI-generated response text for clarity (#12517)GitHub Copilot
  • c7280463fix: Add Vary: Accept header to docs markdown endpoint (#11759)GitHub Copilot

What was excluded

Commits in window1,623
Merge commits removed−0
CI / dependency bots removed−361
Considered1,262

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 vercel/turborepo

Scan another repository

Try