FalkorDB

Active
GitHub Rust NOASSERTION

Description

A high-performance graph database built on GraphBLAS, optimized for LLM and GraphRAG scenarios with real-time knowledge graph construction and querying for graph-structured AI agent retrieval.

Key Features

  • Graph database built on sparse matrices using linear algebra for efficient querying
  • OpenCypher query language support with proprietary extensions
  • Property Graph model with attributes on both nodes and relationships
  • Deeply optimized for LLM and GraphRAG scenarios with ultra-low query latency
  • Multi-tenant architecture supporting real-time knowledge graph construction
  • Docker one-click deployment with built-in web interface and multi-language clients

Use Cases

💡 Long-term memory and knowledge graph storage for AI agents
💡 GraphRAG-enhanced retrieval and reasoning for large language models
💡 Real-time threat relationship analysis in cloud security
💡 Complex relationship network analysis for financial fraud detection
💡 Entity relationship and behavioral pattern modeling for recommendation systems

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (5.8k stars)
  • Established track record (3 years in production)

⚠️ Limitations

  • High issue backlog (667 open issues)
  • No clear open-source license

Quick Start

Run docker run -p 6379:6379 -p 3000:3000 -it --rm falkordb/falkordb to start, then visit http://localhost:3000 in your browser for the web interface, or use the FalkorDB Python client to connect and execute Cypher queries.

Related Projects

HelixDB

5.9k · Rust
Active A+

An open-source graph-vector database built from scratch in Rust, combining graph database and vector retrieval capabilities to provide AI agents with unified storage for both knowledge graphs and semantic search.

graph-databasevector-databaserag +2
  • · Graph-vector database combining graph traversal and vector similarity search in one system
  • · Rust-based engine for high performance with low resource consumption
  • · TypeScript and Rust SDKs with declarative query DSL for building queries

Memgraph

4.4k · C++
Active B

High-performance open-source in-memory graph database built in C++, Cypher-compatible, designed for GraphRAG, AI memory, agentic AI, and real-time graph analytics with native streaming and Kafka integration.

graph-databasegraphragai-memory +3
  • · In-memory graph storage — high-performance C++ implementation with nanosecond-level traversal
  • · Cypher-compatible — supports openCypher query language and reuses the Neo4j ecosystem
  • · GraphRAG-native — built-in vector indexing and graph algorithms to simplify retrieval-augmented generation

GraphRAG

35.8k · Python
Active A+

A modular graph-based Retrieval-Augmented Generation system by Microsoft that uses LLMs to extract structured knowledge graphs from text, enabling global and local community summarization queries.

graphragragknowledge-graph +3
  • · Knowledge Graph Construction — Auto-extract entities and relations from unstructured text using LLMs
  • · Community Detection & Summarization — Leiden algorithm-based graph community detection with hierarchical summaries
  • · Global Queries — Answer cross-document reasoning questions via community summaries

HippoRAG

4.0k · Python
Active A+

NeurIPS 2024 RAG framework inspired by human long-term memory, combining knowledge graphs with personalized PageRank for continuous knowledge integration in LLMs.

ragknowledge-graphlong-term-memory +2
  • · Neurobiologically inspired RAG framework modeled after human hippocampal memory system
  • · Knowledge graph construction with personalized PageRank for associative multi-hop retrieval
  • · Continuous non-parametric learning that integrates new knowledge without retraining