63.5%

of 288 commits were committed by an AI agent — a floor, not an estimate

63.5% agent · top contributor 48.6%8 contributors

team

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

183

agent commits

105

human commits

agent contributors

48.6%

largest contributor

Assisted or autonomous

183assisted

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: 96.3%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code

Anthropic

183

63.5%

Verify it yourself

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

55c7914achore(backlinks): drop the redundant in-try redactionClaude Code
e02c3e6bfix(release): redact the key on every error path and scope the installer tClaude Code
52197c2dfix(release): address the fresh-context review of the v2.3.1 branchClaude Code

What was excluded

Commits in window	308
Merge commits removed	−15
CI / dependency bots removed	−5
Considered	288

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 AgriciDaniel/claude-seo

Scan another repository

Try