NornicDB is a high-performance, Neo4j-compatible graph database built for AI agents and advanced knowledge systems. It features intelligent data management, GPU acceleration, and automated relationship discovery.

What intelligent features does NornicDB offer for AI applications?

NornicDB includes native embeddings, GPU-accelerated vector search, intelligent memory tiers (Episodic, Semantic, Procedural) with decay, and automated relationship discovery based on embeddings and co-access patterns.

How is NornicDB compatible with Neo4j?

NornicDB fully supports the Bolt Protocol and Cypher Query Language, making it a drop-in replacement for Neo4j. You can use existing Neo4j drivers and applications with NornicDB without code changes.

How does NornicDB's performance compare to Neo4j?

Benchmarks show NornicDB offers significant performance advantages, with some queries running up to 52 times faster than Neo4j. It also boasts a lower memory footprint and faster cold start times.

NornicDB

Name: NornicDB
Author: orneryd

byorneryd

•

101

数据库管理

数据科学与机器学习

API 开发

Provides a high-performance, Neo4j-compatible graph database designed for AI agents, offering intelligent features like native embeddings, GPU-accelerated search, and automated relationship discovery.

关于

NornicDB is a high-performance graph database designed for AI agents and knowledge systems. It speaks Neo4j's language (Bolt protocol + Cypher) so you can switch with zero code changes, while adding intelligent features that traditional databases lack. NornicDB automatically discovers and manages relationships in your data, weaving connections that let meaning emerge from your knowledge graph. It offers advanced capabilities like GPU-accelerated vector search, intelligent memory tiers, and a built-in AI assistant, making it ideal for evolving knowledge systems and sophisticated RAG systems.

主要功能

Native GPU-accelerated Vector Search with natural language queries
70 GitHub stars
Neo4j Compatibility (Bolt Protocol & Cypher Queries)
Heimdall AI Assistant for database interaction and a customizable plugin system
Automated Relationship Discovery via embeddings, co-access, and temporal proximity
Intelligent Memory Tiers (Episodic, Semantic, Procedural) with decay

使用案例

Persistent, queryable memory for LLM agents
Vector + graph retrieval in RAG systems
Auto-organizing knowledge bases