← the index
tobi/qmd ↗
12.9%
of 396 commits were committed by an AI agent — a floor, not an estimate
12.9% agent · top contributor 11.8%29 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

51
agent commits
345
human commits
29
agent contributors
11.8%
largest contributor

Assisted or autonomous

51assisted
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: 22.8%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic5112.9%

Verify it yourself

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

  • b7b97911fix(llm): distinguish an unreadable model file from a confirmed-bad oneClaude Code
  • f8352d73fix(update): don't run a checked-in .qmd config's update commands unattendClaude Code
  • 446c2a65fix: make prepare script cross-platform so npm install works on WindowsClaude Code

What was excluded

Commits in window524
Merge commits removed−128
CI / dependency bots removed−0
Considered396

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 tobi/qmd

Scan another repository

Try