Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

A fast Node.js package manager

01Result

aubepkg/aube ↗

aubepkg/aube AI coding statistics: 33.9%

of 1,153 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

33.9% agent · top contributor 96.2%7 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

391

agent commits

762

other considered commits

agent contributors

96.2%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

391assisted

0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Peak month: 49.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	384	33.3%
Cursor Agent	Anysphere	8	0.7%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

2f05cf22 on GitHubfix(resolver): guard primer data rerun-if-changed on file existence (#1540Claude Code
6dff106e on GitHubfeat(resolver): add blockExoticSubdepsExclude to allow named packages (#15Claude Code
04b0605c on GitHubci: reference local reusable workflows with self-repository syntax (#1539)Claude Code
97ad2d4a on GitHubrefactor: replace clap with usage (#1336)Cursor Agent
f867521a on GitHubfix(install): close pnpm-lock.yaml parity and re-resolution gaps (#896)Cursor Agent
b24c0a25 on GitHubfix(install): keep nested pnpm-workspace.yaml as a hard workspace boundaryCursor Agent

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window	1,294
Merge commits removed	−0
CI / dependency bots removed	−141
Considered	1,153

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Rust AI coding statisticsCompare evidence across Rust repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli aubepkg/aube

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	49.7%	386
2026-05	41.7%	302
2026-06	14%	93
2026-07	24%	154
2026-08	8.7%	150
2026-09	14.7%	68