switchboard
L

LightRAG

Featured

by HKU Data Science Lab

Builds a graph-based retrieval index over documents so agents can answer questions spanning many sources, served through a standalone API server.

4
Skills
None
Auth
No
Streaming
No
Push

Skills

Graph Index

Builds an entity and relationship graph from raw documents to support multi-hop retrieval.

Hybrid Query

Combines vector similarity with graph traversal to retrieve context pure embedding search misses.

Incremental Update

Adds new documents to an existing index without rebuilding the whole knowledge graph.

API Serving

Serves retrieval over HTTP through a standalone server that agent harnesses can call directly.

Memory & StateResearch & KnowledgeVector Databasesgraph-ragretrievalknowledge-graphembeddingsdocument-indexingquestion-answeringmemory-backend
Visit Agent

Related Agents

C

Cognee

Builds queryable memory for agents by turning documents and conversations into a knowledge graph plus vector store, sel…

Memory & StateVector Databases
APIMCPCLI
3 skillsAPI Key
A

Algolia

Hosted search and discovery API with typo tolerance, faceting, and vector search, callable directly for agent retrieval…

Research & KnowledgeVector Databases
API
0 skillsAPI Key
C

Codebase Memory MCP

Indexes repositories into a persistent tree-sitter knowledge graph of functions, classes, call chains, and HTTP routes,…

Code & DevToolsMemory & State
MCPCLI
5 skillsNone
G

Graphify

Maps a codebase, docs, PDFs, and media into a queryable knowledge graph so AI coding assistants trace and cite paths in…

Code & DevToolsResearch & Knowledge
CLIMCP
5 skillsNone
lightrag
Builds a graph-based retrieval index over documents so agents can answer questions spanning many sources, served through a standalone API server.
fields
nameLightRAG
providerHKU Data Science Lab
urlhttps://github.com/HKUDS/LightRAG
categoriesmemory-state · research · vector-databases
accessapi · cli
authnone
streamingfalse
pushfalse
verifiedtrue
tagsgraph-rag, retrieval, knowledge-graph, embeddings, document-indexing, question-answering, memory-backend
skills
graph-indexGraph IndexBuilds an entity and relationship graph from raw docume…
hybrid-queryHybrid QueryCombines vector similarity with graph traversal to retr…
incremental-updateIncremental UpdateAdds new documents to an existing index without rebuild…
api-servingAPI ServingServes retrieval over HTTP through a standalone server …
→ https://github.com/HKUDS/LightRAG