nano-graphrag and graphrag-api
One project provides a GraphRAG implementation that can be integrated into applications, while the other offers a server for accessing GraphRAG functionalities, suggesting they are complements where the server could potentially utilize or expose the implementation.
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 graphrag-api
noworneverev/graphrag-api
GraphRAG Server
FastAPI wrapper exposing Microsoft GraphRAG's four search modes (Global, Local, DRIFT, Basic) through REST endpoints, enabling flexible querying across knowledge graphs at different abstraction levels. Operates on pre-indexed GraphRAG project directories containing output artifacts and configuration, with tunable parameters like community hierarchy depth and extraction settings. Integrates seamlessly with the GraphRAG Visualizer frontend or custom clients via standard HTTP APIs.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work