NornicDB
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'
What is NornicDB?
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.
Overview of NornicDB
What it is
NornicDB is a graph database for workloads that need graph traversal, vector retrieval, and historical truth in the same system. It speaks Neo4j's language through Bolt and Cypher, and exposes REST, GraphQL, and gRPC interfaces. It can preserve Qdrant-style client workflows. The architecture draws from research in Temporal GraphRAG, agent memory systems, event-sourced decision memory, and persistence semantics for AI agents. NornicDB implements Snapshot Isolation at the storage layer, with each transaction anchored to a specific MVCC version.
Key features
- Neo4j-compatible by default: Bolt + Cypher support for existing drivers and applications.
- Built for AI-native workloads: vector search, memory decay, and auto-relationships are first-class features.
- Graph, vector, and ledger semantics in one engine: hybrid retrieval, graph traversal, canonical graph ledger modeling, tritemporal facts, as-of reads, txlog queries, and receipts.
- Protocol flexibility: REST, GraphQL, Bolt/Cypher, Qdrant-compatible gRPC, and additive Nornic gRPC on the same platform.
- Hardware-accelerated execution: Metal/CUDA/Vulkan pathways.
- Operational flexibility: full images (models included), BYOM images, and headless API-only deployments.
- Snapshot Isolation with MVCC, repeatable reads within a transaction, conflict detection at commit, and explicit historical reads.
Use cases
- Agent and Graph-RAG systems: replacing a Neo4j + Qdrant + embeddings stack with a single deployment for task tracking, dependency graphs, and retrieval pipelines.
- Translation and evaluation workflows: replacing a document store plus embeddings pipeline with a single deployment for graph-native retrieval and faster aggregation paths.
Getting started
bash # Homebrew brew tap orneryd/nornicdb && brew install nornicdb && brew services start nornicdb # arm64 / Apple Silicon docker run -d --name nornicdb -p 7474:7474 -p 7687:7687 -v nornicdb-data:/data timothyswt/nornicdb-arm64-metal-bge:latest # amd64 / CPU only docker run -d --name nornicdb -p 7474:7474 -p 7687:7687 -v nornicdb-data:/data timothyswt/nornicdb-amd64-cpu-bge:latest Open http://localhost:7474 for the admin UI. For NVIDIA CUDA hosts, use timothyswt/nornicdb-amd64-cuda-bge:latest. For Vulkan hosts, use timothyswt/nornicdb-amd64-vulkan-bge:latest.
License and pricing
License: MIT. Pricing: open source (free).
Based on the project's public README and repository metadata.
