QVAC
Beginner

File organization

25 min · Desktop

A folder that sorts itself, without your files leaving the machine

Auto-categorize a messy folder - PDFs, images, code, archives - and preview the whole reorg before anything moves, fully on-device.

View on GitHubDownload as Markdown
quick-start.sh
git clone https://github.com/tetherto/qvac-examples
cd qvac-examples/qvac-desk-tidy
npm install
npm start

QVAC Desk Tidy is an illustrative example that reads the files in a folder and sorts them into categories you define, entirely on-device. It reads PDFs and text files for content, uses vision analysis on images, and falls back to file extension for code and archives - then shows you the full reorganization plan before moving a single file.

Prerequisites

  • Node.js 22.17 or later

  • 8 GB RAM minimum, 16 GB recommended

  • 0.3 GB disk for text-only categorization, up to 1.8 GB if sorting images

  • GPU optional - CPU works fine

  • A folder you don't mind reorganizing (moves are reversible)

Run the diagnostic tool to confirm RAM, disk, and GPU support before pulling any models.

doctor.sh
npx -y @qvac/cli doctor

Clone qvac-examples and install the desk-tidy demo's dependencies.

setup.sh
git clone https://github.com/tetherto/qvac-examples
cd qvac-examples/qvac-desk-tidy
npm install

Final result

  • Files read by content - PDFs and text parsed, images assessed with vision analysis, code/archives sorted by extension

  • Full reorganization plan reviewed and approved before any file moved

  • Files moved with collision-safe naming

  • Every move journaled and reversible

  • Nothing left the machine - no upload, no cloud step

QVAC Desk Tidy is an illustrative example, not a QVAC product - review the plan before applying it, and keep a backup until you trust its categorization on your files. Fork it from github.com/tetherto/qvac-examples and swap in your own categories or scheduling.

MORE LLM RECIPES

A security camera that sees and reasons, fully on-device

Detect people, vehicles, and animals, reason about risk with a vision-language model, and never send a frame off the machine.

Intermediate

30 min · Desktop

Ask your database in plain English, fully on-device

Turn plain-English questions into read-only SQL against your own database, with a local model that never lets your row data leave the machine.

Intermediate

30 min · Desktop

Build this

Build this with the QVAC SDK

Everything here runs on-device. Grab the SDK and ship your own version.

npm install @qvac/sdk
Get the SDKRead the docs