LEANN and loco-rag-engine
These are **competitors**: both provide self-contained, privacy-preserving RAG systems designed to run locally without cloud dependencies, targeting the same use case of on-device retrieval-augmented generation.
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 loco-rag-engine
madhavmadupu/loco-rag-engine
LOCO (Local-Only Contextual Orchestration) is designed for organizations and individuals who need the power of RAG without the privacy risks or costs of cloud-based LLMs.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work