This project provides an AI-powered local file organizer designed for users overwhelmed by digital clutter. It leverages on-device AI models (Llama3.2 3B and Llava v1.6) to scan, understand, and restructure files, ensuring complete privacy as no data leaves the user's machine.

How It Works

The tool employs a dual-AI approach: Llama3.2 3B analyzes text files for content summarization and relevant naming, while Llava v1.6 processes images to provide context-aware categorization. This allows for intelligent restructuring of files into a more organized directory hierarchy, improving accessibility and retrieval. The entire AI processing pipeline is handled locally via the Nexa SDK, eliminating the need for internet connectivity or external API calls.

Quick Start & Requirements

• Install: python main.py
• Prerequisites: Python 3.12+, Anaconda/Miniconda, Git, Tesseract OCR (for text extraction from PDFs/images).
• Nexa SDK Installation: Requires specific commands for CPU, macOS Metal GPU, or detailed instructions for CUDA/AMD GPU support.
• Setup: Estimated setup time depends on Nexa SDK and Tesseract installation.
• Docs: Nexa SDK Installation

Highlighted Details

• Featured by Nexa Gallery and Nexa SDK Cookbook.
• Supports dry run mode to preview changes before execution.
• Offers sorting by content, date, and type.
• Added support for .md, .excel, .ppt, and .csv file types.
• Includes a real-time progress bar for file analysis.

Maintenance & Community

• Project is actively updated, with v0.0.2 released in September 2024.
• Nexa team is assisting with cross-platform executable builds.
• Roadmap includes features like Copilot Mode (chat-based sorting) and broader file type support (ebooks, audio, video).

Licensing & Compatibility

• Dual-licensed under MIT and Apache 2.0.
• Permissive licenses suitable for commercial use and integration with closed-source projects.

Limitations & Caveats

• Currently in early development (v0.0.2), with several features still on the roadmap.
• Requires manual installation of Tesseract OCR and careful setup of the Nexa SDK, which may vary by GPU hardware.