XMUDeepLIT/MemGraphRAG

MemGraphRAG is a memory-based multi-agent system for Graph Retrieval-Augmented Generation that organizes knowledge into schema, fact, and passage layers, enabling conflict-aware construction and memory-derived graphs.

View on index · View in 3D Map

Related repos

• Modularizes and decouples graph-based retrieval-augmented generation methods
• Builds knowledge graphs for agents
• Graph-based MCP memory server for AI agents
• Agentic workflow for graph retrieval-augmented generation
• Graph-native memory system for AI agents
• Graph native agentic system
• Persistent knowledge graph for coding agents
• Knowledge graph engine for OpenClaw memory
• lightweight GraphRAG implementation for building knowledge graph-based retrieval with LLMs
• Builds knowledge graphs from documents with WebGPU acceleration