{"id":"lightrag","name":"LightRAG","maker":"HKUDS","url":"https://github.com/HKUDS/LightRAG","repo":"HKUDS/LightRAG","package":"pypi:lightrag-hku","summary":"A Python library for retrieval-augmented generation that builds a knowledge graph from documents and queries both graph and vectors.","details":"LightRAG extracts entities and relations from text with a model, stores them with embeddings, and answers queries in several retrieval modes. It supports multiple storage back ends such as Neo4j, PostgreSQL and Milvus, and includes a server with a web interface and API.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"retrieval","category_name":"Vector databases and retrieval","page":"https://modelmoot.com/tools/lightrag","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}