← the index
vercel/turborepo ↗
7.3%
of 1,462 commits were committed by an AI agent — a floor, not an estimate
7.3% agent · top contributor 74.5%18 contributors
team

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

106
agent commits
1,356
human commits
18
agent contributors
74.5%
largest contributor

Assisted or autonomous

104assisted
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

Jan26
Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 14.1%. Bars are scaled to that peak, not to 100%.

Which agents

Cursor AgentAnysphere624.2%
Claude CodeAnthropic422.9%
GitHub CopilotGitHub40.3%

Verify it yourself

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

  • 8a6b0f7efix: Harden Go workspace diagnostics (#13964)Cursor Agent
  • 7f36a42fdocs: Document experimental native Go workspaces (#13963)Cursor Agent
  • a1cbfaa8test: Add end-to-end Go prune and cache coverage (#13962)Cursor Agent
  • e901550echore: Scope panic lint allows in hash crates to tests and generated code Claude Code
  • 935ee2c0feat(repository): Expose flat lockfile package list for metrics (#13859)Claude Code
  • 658fd546fix: don't use eprintln! in the panic hook (#13637)Claude Code
  • 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 window1,908
Merge commits removed−0
CI / dependency bots removed−446
Considered1,462

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