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.
Achieves extreme storage efficiency through graph-based selective recomputation with high-degree preserving pruning, computing embeddings on-demand rather than storing them. Natively integrates with Claude via MCP and supports semantic search across diverse personal data sources—file systems, emails, browser history, chat logs, and live platforms like Slack and Twitter—all on-device without cloud dependency.
10,303 stars. Actively maintained with 12 commits in the last 30 days. Available on PyPI.
Stars
10,303
Forks
894
Language
Python
License
MIT
Category
Last pushed
Mar 08, 2026
Commits (30d)
12
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.
Related tools
byerlikaya/SmartRAG
Multi-Modal RAG for .NET — query databases, documents, images and audio in natural language....
mrutunjay-kinagi/ragsearch
This project aims to build a Retrieval-Augmented Generation (RAG) engine to provide...
aws-samples/layout-aware-document-processing-and-retrieval-augmented-generation
Advanced document extraction and chunking techniques for retrieval augmented generation that is...
Omkar-Wagholikar/adora
Python package that makes it easy to spin up a custom Retrieval-Augmented Generation (RAG) pipeline.
leewaay/ragcar
RAGCAR: Retrieval-Augmented Generative Companion for Advanced Research