A privacy-focused CLI tool that automates OCR and local AI processing to intelligently organize and archive documents.
Vaultify transforms your messy scans and images into an organized archive. By leveraging Tesseract.js for text extraction and Ollama for local AI analysis, your sensitive documents never leave your machine.
- Local-First AI: Powered by Ollama, ensuring 100% data privacy.
- Automated OCR: Extracts text from images and PDFs using Tesseract.js.
- Smart Organization: Recursively crawls your directories and mirrors the structure in a
vaultified/folder. - Modern CLI: Beautiful terminal interface with real-time progress thanks to Ora and Chalk.
- Developer Friendly: Built with TypeScript, Biome for linting, and Vitest for reliability.
- Node.js (v20.10.0 or higher)
- Ollama installed and running:
ollama pull deepseek-r1
Run Vaultify directly using npx by pointing it to your documents directory:
npx @treast/vaultify ./Documents| Flag | Description | Default |
|---|---|---|
--model |
AI provider | ollama |
--ollama-api-url |
The Ollama endpoint | http://127.0.0.1:11434/api/generate |
--ollama-model |
The Ollama model to use for analysis | deepseek-r1 |
--language |
OCR language (ISO 639-2) | fra |
--output |
The name of the output folder | vaultified |
If you want to contribute or build from source:
git clone https://github.com/Treast/vaultify.git
cd vaultify
npm install
npm run buildWe use Biome for linting:
npm run ci-check # Lint & Format checkThis project is licensed under the GNU General Public License v3.0. See the LICENSE file for the full text.
Built with ❤️ for privacy.