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.
High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in C++.
A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.
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.
The cognitive database. A new class of data storage. Not a vector store, not a graph DB, not a RAG wrapper. Ebbinghaus decay, Hebbian learning, and Bayesian confidence are engine-native primitives. Memories evolve on their own. MCP-native. Single binary.
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.
