memgraph/memgraph

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

KuzuDB fork maintained by Vela Partners. Embedded graph database for AI agent memory with concurrent multi-writer support. 374x faster than Neo4j on path queries. Cypher, vector search, full-text search. In-process, zero infrastructure. MIT licensed.

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

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.

Open-source tools for AI on Memgraph: persistent agent memory, knowledge graphs, GraphRAG, and integrations for LangChain, LightRAG, and MCP.

mnestic is a maintained fork of CozoDB (transactional relational-graph-vector DB with Datalog), tuned as a substrate for agentic memory.

RushDB is an open-source database for AI. It records fields, types and values on every write, so agents can read the schema before they query.

The one data index for your agentic applications