LlamaFS: A tool based on Llama 3 that automatically helps you sort files on your computer
what it can do
LlamaFS is a self-organizing file manager. It automatically renames and organizes files based on their content and well-known conventions such as time. It supports multiple files, even images (via Moondream) and audio (via Whisper).
LlamaFS runs in two “modes”-as a batch job (batch mode) and as an interactive daemon (monitor mode).
in batch mode
In monitor mode, LlamaFS launches a daemon that monitors your directory. It intercepts all file system operations, updates i and uses your recent edits in context to proactively learn and manipulate, so you won’t learn to predict how to rename files. For example, if you create a folder for 2023 tax documents and start moving 1-3 files within it, LlamaFS will automatically create it and move it to the right!
Send all my personal files to the API provider?
It has a “stealth mode” toggle switch that allows you to route every request through Olama instead of Groq. Since they use the same Llama 3 model, the performance is the same.
How to build it
We built LlamaFS on the Python backend, and used Groq to use the Llama3 model to summarize the file content and structure the tree. For local processing, we integrated Ollama running the same model to ensure privacy in stealth mode. The front end is made in Electron and provides a stylish, user-friendly interface that allows users to interact with the suggested file structure before completing changes.
Very fast! (For LLM standards)! In monitor mode, most file operations take less than 500 milliseconds to process. This is because of our smart caching, which selectively rewrites parts of the index based on the minimum necessary file system differences. Of course, there is Groq’s ultra-fast inference API.
It works immediately-there is very little resistance to use, and almost everyone encounters this problem. We started using it ourselves on this project (very Meta)
If you want to learn more, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
Github：https://github.com/iyaja/llama-fs
Oil tubing: