project-minigraf/minigraf

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.

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

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.

the open-source Context/Knowledge Layer Database

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

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.

Object-storage native graph database with branching and typed ontology

Embedded single-file knowledge graph database with vector search and full-text search for AI/RAG apps

Fluree database library