31.3%

of 99 commits were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 99 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

31.3% agent · top contributor 61.3%6 contributors

team

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

agent commits

human commits

agent contributors

61.3%

largest contributor

Assisted or autonomous

29assisted

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: 62.1%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	18	18.2%
GitHub Copilot	GitHub	8	8.1%
Cursor Agent	Anysphere	5	5.1%

Verify it yourself

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

573d4f33fix(openapi): drop function-valued properties from generated schemas (#758Claude Code
3a77dc4dbuild(deps): upgrade docusaurus to 3.10.2 (#7583)Claude Code
4359916fbuild(deps): upgrade lerna to v10 (#7582)Claude Code
340811baci(example): fix Playwright e2e ffmpeg failures (#7412)GitHub Copilot
492bacf3chore: Add cache checks for openapi router fixtures (#7296)GitHub Copilot
59f2cdb3chore: Review stale skills (v11.16.0) (#7295)GitHub Copilot
774b244cfix(ci): restore tests package version (#7393)Cursor Agent
3c5252ffchore(www): Add Legora to website logos (#7358)Cursor Agent
331db6d1build: upgrade drizzle in next-sse-chat example (#7351)Cursor Agent

What was excluded

Commits in window	166
Merge commits removed	−0
CI / dependency bots removed	−67
Considered	99

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 trpc/trpc

Scan another repository

Try