NornicDB

Overview

NornicDB is a high-performance graph and vector database that combines temporal MVCC with sub-ms HNSW search capabilities. It provides Neo4j Bolt/Cypher compatibility and Qdrant gRPC support, making it easy to switch existing applications. The database includes intelligent features such as schemas, managed embeddings, LLM reranking, GPU acceleration, and an integrated MCP server for enhanced AI workflows. It achieves 12x-52x performance improvements over Neo4j in benchmarks while providing hybrid graph+vector retrieval in a single engine.

Try asking AI

After installing, here are 3 things you can ask your AI assistant:

• query_neo4j

  Execute Cypher queries on the graph database

  Try:Find all nodes with label PersonTry:Create a new relationship between two nodes
• vector_search

  Perform vector similarity search using HNSW algorithm

  Try:Find similar documents to the one about machine learningTry:Search for products with vector embeddings
• graph_traversal

  Traverse the graph structure with path-finding capabilities

  Try:Find the shortest path between two nodesTry:Traverse all nodes connected to a starting node
• create_node

  Create a new node in the graph database

  Try:Create a new User node with email propertyTry:Add a new Product node with price and description
• create_relationship

  Create a new relationship between two nodes

  Try:Connect a User node to an Order nodeTry:Create a LIKES relationship between a Person and a Movie
• update_node

  Update properties of an existing node

  Try:Update the name property of a Person nodeTry:Change the status of an Order node
• delete_node

  Delete a node and its relationships from the graph

  Try:Remove a User node and all connected relationshipsTry:Delete an obsolete Product node
• hybrid_retrieval

  Perform combined vector search and graph traversal in one query

  Try:Find similar documents and their connected conceptsTry:Search for products and their related reviews
• create_vector_index

  Create a new vector index for similarity search

  Try:Create an index for document embeddingsTry:Set up a vector index for product features
• historical_read

  Query past versions of the graph using MVCC

  Try:Check how the graph looked last weekTry:Find previous values of a node property
• schema_constraint

  Add or remove constraints on node properties

  Try:Create a unique constraint for email propertiesTry:Add a NOT NULL constraint for name properties
• graph_rollback

  Rollback the graph to a previous transaction state

  Try:Rollback to the state before the last batch of updatesTry:Restore graph from yesterday's backup

Note: Tool names inferred from documented database capabilities and common graph database operations. The README mentions Neo4j compatibility and vector search but doesn't provide explicit MCP tool names.

Comparable tools

Installation

# 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

git clone https://github.com/orneryd/NornicDB.git
cd NornicDB
go build -o nornicdb ./cmd/nornicdb
./nornicdb serve

{
  "mcpServers": {
    "nornicdb": {
      "command": "nornicdb",
      "args": ["mcp"]
    }
  }
}

On Hacker News

Recent discussion from the developer community.

• Cutting Cypher Query Latency: Streaming Traversal and Query Shape Specialization▲ 1
  Story by orneryd · 2026-02-26

Compare NornicDB with