yichuan-w/LEANN
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
This tool helps you turn your computer into a private AI assistant for searching through all your digital information. It takes your personal documents, emails, browser history, chat logs, and even live social media feeds, allowing you to ask questions and get answers from them. Anyone who needs to quickly find information across a vast and varied personal data collection without relying on cloud services would use this.
10,303 stars. Actively maintained with 9 commits in the last 30 days. Available on PyPI.
Use this if you need to perform intelligent searches across millions of your personal documents and digital conversations, like finding specific emails, chat messages, or browsing history, all while keeping your data private on your own device.
Not ideal if you primarily need to search public web content or collaborate with others on shared datasets that are already hosted in a traditional cloud-based system.
Stars
10,303
Forks
894
Language
Python
License
MIT
Category
Last pushed
Mar 08, 2026
Commits (30d)
9
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/yichuan-w/LEANN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Compare
Related tools
byerlikaya/SmartRAG
Multi-Modal RAG for .NET — query databases, documents, images and audio in natural language....
aws-samples/layout-aware-document-processing-and-retrieval-augmented-generation
Advanced document extraction and chunking techniques for retrieval augmented generation that is...
sourangshupal/simple-rag-langchain
Exploring the Basics of Langchain
sion42x/llama-index-milvus-example
Open AI APIs with Llama Index and Milvus Vector DB for Retrieval Augmented Generation (RAG) testing
Maverick0351a/neuralcache
NeuralCache is a drop-in reranker for Retrieval-Augmented Generation (RAG) that learns which...