LEANN and rag-system-ollama
Both tools offer local-first RAG systems, but LEANN focuses on efficient storage and privacy for general RAG, while rag-system-ollama specializes in high-performance orchestration of small language models via Ollama and LangGraph with advanced search capabilities, making them **competitors with different technical priorities and approaches to achieving local RAG**.
About LEANN
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.
About rag-system-ollama
darkzard05/rag-system-ollama
Advanced local-first RAG system powered by Ollama and LangGraph. Optimized for high-performance sLLM orchestration featuring adaptive intent routing, semantic chunking, intelligent hybrid search (FAISS + BM25), and real-time thought streaming. Includes integrated PDF analysis and secure vector caching.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work