FalkorDB/FalkorDB

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

What it solves

FalkorDB is a high-performance, multi-tenant graph database designed to provide exceptionally low latency for information delivery. It is specifically tailored to power Generative AI applications, AI agent memory, cloud security, and fraud detection by acting as a high-speed Knowledge Graph.

How it works

Unlike traditional graph databases, FalkorDB leverages sparse matrices to represent the adjacency matrix of the graph and employs linear algebra for query execution. It is implemented as a Redis module in Rust, adhering to the Property Graph Model and supporting the OpenCypher query language (with proprietary extensions).

Who it’s for

It is intended for developers building LLM-powered applications that require fast graph-based retrieval, as well as professionals working in cloud security, fraud detection, and other domains requiring high-performance relationship mapping.

Highlights

  • Sparse Matrix Representation: Optimizes storage and performance by using sparse matrices for adjacency.
  • Linear Algebra Querying: Increases computational efficiency during query execution.
  • OpenCypher Support: Compatible with the OpenCypher query language for flexible graph querying.
  • Multi-tenant Architecture: Designed to handle multiple tenants efficiently.
  • Broad Client Support: Provides official libraries for Java, Python, Node.js, Rust, and Go.

Related

  • Project
    vesoft-inc/nebula

    A distributed, scalable graph database designed for large-scale graph analytics and millisecond latency in applications like knowledge graphs and recommendation systems.

  • Project
    FalkorDB/code-graph

    CodeGraph is a tool that transforms codebases into interactive knowledge graphs stored in FalkorDB, enabling developers to visualize dependencies and query code structure using LLM-powered GraphRAG.

  • Project
    infiniflow/infinity

    An AI-native database providing high-speed hybrid search across dense and sparse embeddings, tensors, and full-text for LLM and RAG applications.

  • Project
    sknetwork-team/scikit-network

    A Python library for machine learning on graphs that uses sparse matrices for memory-efficient network analysis.

  • Project
    HelixDB/helix-db

    HelixDB is an Apache‑2.0 graph database written in Rust that natively supports vector (ANN) search and BM25 full‑text search. It lets you store entities, relationships, embeddings, and text together and query them via a unified JSON API or Cypher. SDKs exist for Rust, TypeScript, Python, and Go, and a CLI provides local dev, embedded mode, and a managed Helix Cloud service.