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.

One home instead of many subscriptions. Yuvomi is a self-hosted family planner: tasks, calendar, budget, meals, shopping, health and more in one PWA on your own server or NAS. Docker, Podman, TrueNAS, Umbrel, Unraid. No tracking, MIT.

01Result

ulsklyc/yuvomi ↗

ulsklyc/yuvomi AI coding statistics: 20.4%

of 3,401 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

20.4% agent · top contributor 25.8%35 contributors

org-wide

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

693

agent commits

2,708

other considered commits

agent contributors

25.8%

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

686assisted

7autonomous

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: 70.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	681	20%
GitHub Copilot	GitHub	9	0.3%
Cursor Agent	Anysphere	3	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

cc6d707b on GitHubfix(contacts,tasks,pantry): report the refresh failure the manager cannot Claude Code
50363352 on GitHubfix(tasks): rebuild the filter bar after every category change, not only aClaude Code
8a87a5cd on GitHubfix(shopping,inventory): let a refresh lose the race and speak up when it Claude Code
a0f6bbc0 on GitHubfix(sync): lower no-op sync logs to debugGitHub Copilot
3284abfc on GitHubDisable filters in app-content scroll containerGitHub Copilot
df1852d9 on GitHubInitial planGitHub Copilot
ffa0b1dd on GitHubfeat(ui): polish birthdays as composition reference demoCursor Agent
d1776423 on GitHubfeat(ui): Page Composition System (PAGE-COMPOSITION.md)Cursor Agent
c4e2339c on GitHubfeat: give third-party modules the same surfaces as coreCursor 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	3,866
Merge commits removed	−414
CI / dependency bots removed	−51
Considered	3,401

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →JavaScript AI coding statisticsCompare evidence across JavaScript 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 ulsklyc/yuvomi

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	70.7%	164
2026-04	30.4%	474
2026-05	52.9%	312
2026-06	40.2%	540
2026-07	0.2%	437
2026-08	3.9%	1042
2026-09	2.1%	432