4.1%

of 1,471 commits were committed by an AI agent — a floor, not an estimate

4.1% agent · top contributor 78.3%13 contributors

team

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

agent commits

1,411

human commits

agent contributors

78.3%

largest contributor

Assisted or autonomous

60assisted

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

Feb26

Mar26

Apr26

May26

Jun26

Jul26

Aug26

Sep26

Peak month: 22.2%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code

Anthropic

4.1%

Verify it yourself

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

7c3b05e2refactor(livewire): make data-sync helpers private (#11578)Claude Code
2018e7f3Validate build-time environment variable names before writing the build .eClaude Code
3d0caa23fix(deployments): apply custom docker options when custom container name iClaude Code

What was excluded

Commits in window	2,306
Merge commits removed	−803
CI / dependency bots removed	−32
Considered	1,471

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 coollabsio/coolify

Scan another repository

Try