12.1%

of 2,535 commits were committed by an AI agent — a floor, not an estimate

12.1% agent · top contributor 52.3%45 contributors

team

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

306

agent commits

2,229

human commits

agent contributors

52.3%

largest contributor

Assisted or autonomous

306assisted

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

Mar26

Apr26

May26

Jun26

Jul26

Aug26

Sep26

Peak month: 52.1%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	250	9.9%
Cursor Agent	Anysphere	34	1.3%
OpenAI Codex	OpenAI	23	0.9%

Verify it yourself

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

e17cdd9drefactor(buzz-acp): point agents at buzz --help instead of a command tableClaude Code
cec5c8fdfix(desktop): let inbox title and message author names truncate under narrClaude Code
dad5a338fix(desktop): keep packaged frontendDist relative so Windows embeds assetsClaude Code
d42d60d6fix(desktop): rename generic attachment action from 'Attach image' to 'AttCursor Agent
cb2a265bfeat(search): parse from:/in:/after:/before: and pass them in the filter (Cursor Agent
89953168fix(desktop): use forward slashes for git credential.helper on Windows (#3Cursor Agent
76f7e5effeat(push): make gateway origin configurable (#7261)OpenAI Codex
f78a32cffeat(mobile): hard-block under-18 users on the store age signal (#4665)OpenAI Codex
cd02b693refactor(relay): extract NIP-29 membership authorization (#7285)OpenAI Codex

What was excluded

Commits in window	2,660
Merge commits removed	−1
CI / dependency bots removed	−124
Considered	2,535

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 block/buzz

Scan another repository

Try