← the index
garrytan/gbrain
61.7%
of 1,064 commits were committed by an AI agent — a floor, not an estimate
61.7% agent · top contributor 56.6%59 contributors
team

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

657
agent commits
407
human commits
59
agent contributors
56.6%
largest contributor

Assisted or autonomous

657assisted
0autonomous

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

Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 98%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic65761.7%
OpenAI CodexOpenAI20.2%

Verify it yourself

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

  • f1fbdfbav0.50.1.0 fix: community fix wave — 21 PR adoptions + 35 verified issue fiClaude Code
  • 43597b19v0.48.5.0 fix: community fix wave — 57 PR adoptions + 42 verified issue fiClaude Code
  • 2efaaf8fv0.48.4.0 feat(search,eval): ranker wave — autocut off, relational rerank Claude Code
  • 77bb9d8cv0.46.32.0 fix: wave-k community train — 54 contributor PRs absorbed, recoOpenAI Codex
  • 87840341v0.31.7 fix-wave: doctor stops crying wolf — 5 community PRs (#798 + #788 OpenAI Codex

What was excluded

Commits in window1,068
Merge commits removed4
CI / dependency bots removed0
Considered1,064

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 garrytan/gbrain

Scan another repository