Vela-Engineering/kuzu

High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in C++.

Absurdly fast embedded graph database with built-in vector search. Rust core, Node.js and Python connectors, GQL, graph algorithms, all in-process with no server.

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 while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

Embedded property graph database built for speed. Vector search and full-text search built in. Implements Cypher.

TuringDB high performance in-memory column-oriented graph database engine

AI memory and a knowledge graph in one SQLite file. Pure Go: vectors, RAG, agent memory, RDF/SPARQL, Cypher, 80+ MCP tools. Works without an embedding model.

Ryu, a fork of Kuzu, is an Embedded Property Graph Database built for speed with vector search and full-text search built in. Implements Cypher.

RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.

The memory & storage engine for AI agents. Multi-model, edge-to-cloud, PostgreSQL-compatible.