A
A
AI File Organizer
1 like
A command-line Digital Asset Manager (DAM) that uses multimodal AI (Google Gemini / Ollama) to automatically rename, tag, and embed structured metadata into your files.
Cost / License
- Free
- Open Source (GPL-3.0)
Platforms
- Windows
- Mac
- Linux
AI File Organizer
1 like
Features
Properties
- Privacy focused
- Lightweight
Features
- Portable
- No Tracking
- Ad-free
- Full-Text Search
- Batch Rename Files
- No registration required
- File Tagging
- Command line interface
Tags
- Metadata
- gemini
- tmsu
- Artificial intelligence
- auto-rename
- Ollama
- exiftool
- Digital Asset Management
AI File Organizer News & Activities
Highlights All activities
Recent activities
- niksavc liked AI File Organizer
- foadsf added AI File Organizer
AI File Organizer information
No comments or reviews, maybe you want to be first?
What is AI File Organizer?
AI File Organizer is a production-ready, cross-platform command-line tool that acts as an intelligent Digital Asset Manager (DAM). Instead of just looking at basic file properties, it leverages multimodal AI (like Google Gemini and Ollama) to read the actual content of your files—whether it's an image, a PDF document, or text.
It analyzes the content and automatically suggests clear, descriptive filenames and structured tags.
Key Features:
- True Multimodality: Native file uploads to Gemini—it "sees" photos and "reads" PDFs.
- Ontology Enforcement: Forces the AI to use specific Key-Value pairs (e.g., year=2026, amount=150.00) for structured organization via TMSU, preventing messy "flat tag" clutter.
- Universal Interoperability: Embeds the AI-generated metadata directly into files via ExifTool (XMP/IPTC tags), making your tags readable by Lightroom, MacOS Finder, and Windows Explorer.
- Cost-Optimized SQLite Cache: Persistently remembers file hashes so you don't pay API costs twice for analyzing the same file.
- RAG-Lite Context: Only feeds the AI relevant tags based on the file's MIME type to improve accuracy and prevent hallucination.
- Local Fallback: Fully supports local, offline execution using Ollama vision models for privacy-focused users.