7.4%

of 524 commits were committed by an AI agent — a floor, not an estimate

7.4% agent · top contributor 71.8%8 contributors

team

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

agent commits

485

human commits

agent contributors

71.8%

largest contributor

Assisted or autonomous

38assisted

1autonomous

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: 33.7%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	25	4.8%
GitHub Copilot	GitHub	13	2.5%
Cursor Agent	Anysphere	1	0.2%

Verify it yourself

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

c9b356b4fix(memo): populate parent relation in comment webhook payload (#6083)Claude Code
797f1ff1feat(web): markdown WYSIWYG editor with raw-mode toggle (#6030)Claude Code
8f137732fix(editor): wire Ctrl+B and Ctrl+I markdown shortcuts to textarea (#6016)Claude Code
6b305799feat: add outline navigation to memo detail sidebar (#5771)GitHub Copilot
45b21530feat: add blur_content attribute to tag metadata settings (#5767)GitHub Copilot
9e040496feat: treat tag setting keys as anchored regex patterns (#5759)GitHub Copilot
ea0892a8feat: add live refresh via Server-Sent Events (SSE) with visual indicator Cursor Agent

What was excluded

Commits in window	526
Merge commits removed	−0
CI / dependency bots removed	−2
Considered	524

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 usememos/memos

Scan another repository

Try