nano-graphrag and biomedical-graphrag
These are ecosystem siblings where one provides a lightweight, general-purpose GraphRAG framework suitable for implementation and experimentation, while the other applies that architectural pattern to a specialized domain (biomedical research) with domain-specific optimizations and knowledge structures.
About nano-graphrag
gusye1234/nano-graphrag
A simple, easy-to-hack GraphRAG implementation
Builds knowledge graphs from text by extracting entities and relationships, then performs retrieval-augmented generation through both global and local graph traversal modes. Supports pluggable components including multiple LLM providers (OpenAI, Bedrock, Ollama), vector databases (FAISS, Milvus, HNSWlib), and graph backends (Neo4j, NetworkX), with full async/await support and MD5-based deduplication for incremental inserts.
About biomedical-graphrag
benitomartin/biomedical-graphrag
A comprehensive GraphRAG (Graph Retrieval-Augmented Generation) system designed for biomedical research
Combines Neo4j knowledge graphs with Qdrant vector embeddings for hybrid biomedical retrieval, ingesting PubMed papers, gene data, and citation networks into a specialized schema covering papers, authors, institutions, genes, and MeSH terms. LLM-powered tool selection routes queries to semantic search or graph traversal, while async processing handles high-volume data collection from external biomedical APIs.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work