Memory control plane for AI Agents in 6 lines of code

Neo4j graph construction from unstructured data using LLMs

A Graph RAG System for Evidenced-based Medical Information Retrieval [ACL 2025]

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes. Then, adding intelligent features like schemas, managed embeddings, LLM reranking+inferrence, GPU accel, Auto-TLP, Memory Decay, and MCP server.

Logic Language for LLMs 🌱🐋🌍 Build Neuro-Symbolic AI for Learning and Reasoning

《动手学SpringAI》包含SSE流/Agent智能体/知识图谱RAG/FunctionCall/历史消息/图片生成/图片理解/Embedding/VectorDatabase/RAG

A SQLite extension that adds graph database capabilities with Cypher query language support and built-in graph algorithms.

"Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation" by Yifan Feng, Hao Hu, Shihui Ying, Xingliang Hou, Shiquan Liu, Mingyuan Yang, Junchang Li, Shaoyi Du, Nanning Zheng, Han Hu, and Yue Gao.

VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.

Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.

Xmem is a India's First open source multi-modal, multi-agentic long‑term memory layer for AI agents.

GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.

OriginTrail Decentralized Knowledge Graph (DKG) is a decentralized knowledge infrastructure for multi-agent AI memory — enabling agents to publish, verify, and query shared knowledge as cryptographically verifiable graph assets across a peer-to-peer network.

[WWW 2025] Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.

A modular Python framework implementing the Model Context Protocol (MCP). It features a standardized client-server architecture over StdIO, integrating LLMs with external tools, real-time weather data fetching, and an advanced RAG (Retrieval-Augmented Generation) system.

Active WIP for experimenting with GraphRAG and Knowledge Graphs

Demo of knowledge graph creation and Graph RAG with BAML and Kuzu

构建一个医疗知识图谱并基于此实现 RAG，并以此实现医学试题的生成

Graph-vector database that queried 1 billion edges for $2.50. Rust, OpenCypher, vector search, 14 graph algorithms. 74M nodes / 1B edges on a single machine.