AI-Software / Desktop
VideoSorterLocal
Organize video collections locally with AI and batch undo.
Categorize videos, add tags and organize folders without sending recordings to the cloud. The Python and PySide6 application combines filenames, metadata, frame OCR and local vision models. BGE-M3 supports content matching, while batch undo lets you reverse file moves after reviewing the results.
Local processing after installing the required models and dependencies. See the usage scope and license terms below. License terms
Key features
Explore the tools you can use in your everyday workflow.
Multi-stage analysis
Combine filenames, metadata, RapidOCR and local vision models with a file fingerprint cache.
Two classification modes
Weight multiple signals or compare sampled frames with BGE-M3 embeddings and voting.
Local AI runtime
Use Ollama or LM Studio offline after setup, with automatic VRAM release on exit.
Tags and learning memory
Generate up to 10 tags, use PL/EN synonyms and store relationships in SQLite.
Folders and batch undo
Move videos into categories, handle filename collisions and reverse a batch in one click.
Metadata and covers
Write titles, tags and thumbnails using FFmpeg and the Windows Property Store.
System requirements
Check your hardware before installing.
- Operating system (OS)
- Windows 10 / 11 (64-bit), Linux (Ubuntu / Debian / Arch), macOS 11+
- Processor (CPU)
- 4-core CPU (Intel Core i5 / AMD Ryzen 5) or Apple Silicon M-Series
- Graphics (GPU)
- Dedicated GPU recommended for local VLM (Ollama / LM Studio) or CPU-only mode
- RAM Memory
- 8 GB RAM (16 GB recommended for local VLM inference & BGE-M3 embeddings)
- Storage / SSD
- 500 MB for application + space for optional local AI models
Downloads
Choose your operating system and package format. Each release includes its version and file size.
Technology stack
VideoSorterLocal
Try it on your computer
Download the trial and test it on your own hardware. Buy the license once, with no subscription.