DevImprint.

Articles

Which repositories AI-assisted commits actually land in

· data story · By DevImprint

Every figure in this article comes from the snapshot taken 4 September 2026 (dff873050215). Later snapshots will differ; thecurrent ranking shows the latest published snapshot.

The public repositories absorbing the most AI-assisted commits in the last 30 days, and why the shape of that list says more than the ranking at the top of it.

On this page

A leaderboard of people answers “who”. The more useful question for anyone deciding how to work is “where”: which codebases are actually absorbing AI-assisted commits, and what kind of work is going into them.

Every figure below comes from the snapshot named at the top of this page. Later snapshots will differ, and the current ranking is always live.

The shape of the list matters more than its top

Two things are worth noticing in the chart below, neither of which is the name in first place.

The distribution is steep. A small number of repositories absorb a large share of the detected commits, and the tail falls away quickly. That is the signature of concentrated agent work: a handful of projects where someone has wired an agent into their normal loop, rather than broad shallow adoption across many codebases.

Most of them are infrastructure, not products. Tooling, pipelines, configuration and test suites dominate. This matches what the tools are good at today: bounded, well-specified changes with fast feedback, where a wrong answer is caught by a test rather than a customer.

Counting caveat, stated once

These totals are built from the repositories named by ranked developers, so a repository whose contributors are not yet ranked is undercounted, and one with many ranked contributors is favoured. It is a ranking of visible activity, not a census. Coverage has the current scan figures.

When the commits happen

The weekday pattern is the other half of the picture. AI-assisted commits are not evenly spread, and the shape tells you something about who is producing them: weekday-heavy suggests professional work inside a normal week, while a flatter distribution points to side projects and personal repositories.

What this does not show

Nothing here measures value. A repository with many AI-assisted commits is not better maintained than one with none, and the tools are heavily represented in exactly the kind of high-volume, low-risk change that inflates commit counts without moving a product forward. Read this as a map of where the tools are being used, and nothing more.

Repositories with the most AI-assisted commits, last 30 days AI-assisted commits outof-place/pod 32,420 aawalton/akasha 20,632 manaflow-ai/cmux 20,126 joshualeestone/kosmos 9,852 happier-dev/happier 9,699 pyhuanglaw/Lawstudent 8,277 bojieli/OpenTallas 8,240 Esposter/Esposter 7,333 Bewinxed/whiffle 7,086 believeinoakland/bio 7,019 ptarjan/cryptic-teacher 6,665 andrewjberman/archive 6,650 Detected AI-assisted commits in public repositories · 33.2% of known repositories scanned · provisional 2026-11-08
Counted from the ranked developers in this snapshot, so a repository whose contributors are not yet ranked is undercounted.
Table view
RepositoryAI-assisted commits (30d)Ranked contributors
outof-place/pod32,4201
aawalton/akasha20,6326
manaflow-ai/cmux20,1264
joshualeestone/kosmos9,8521
happier-dev/happier9,6991
pyhuanglaw/Lawstudent8,2771
bojieli/OpenTallas8,2401
Esposter/Esposter7,3331
Bewinxed/whiffle7,0861
believeinoakland/bio7,0191
ptarjan/cryptic-teacher6,6651
andrewjberman/archive6,65011
AI-assisted commits by day of week, last 30 days AI-assisted commits 569,810 284,905 0 Sun Mon Tue Wed Thu Fri 569,810 Sat Detected AI-assisted commits in public repositories · 33.2% of known repositories scanned · provisional 2026-11-08
Days are UTC as recorded in the commit, not the author’s local time zone.
Table view
Day (UTC)AI-assisted commits
Sun425,784
Mon451,492
Tue454,573
Wed458,876
Thu450,670
Fri437,511
Sat569,810

Tools mentioned

Claude CodeCursorAider

How these numbers are measured · what they cover