orneryd/NornicDB — Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, grap…

Description and use

NornicDB is a high‑performance, distributed database that combines graph and vector search with temporal MVCC, delivering sub‑millisecond HNSW queries, graph traversals, and ultra‑low‑latency writes. It supports Neo4j Bolt/Cypher and Qdrant gRPC APIs for seamless compatibility, while offering advanced features such as schema enforcement, managed embeddings, LLM‑based reranking and inference, GPU acceleration, automatic temporal locality pruning, memory decay, and an MCP server.

Problem

orneryd/NornicDB helps connect AI assistants to real tools and data through a standard protocol.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• connect AI agents to tools
• ship Model Context Protocol servers
• standardize integrations

Evidence

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.

Source