Skip to main content
FalkorDB Docs Banner
FalkorDB is the #1 GitHub repository of the day on Trendshift
Star FalkorDB on GitHubDocker pullsJoin the FalkorDB Discord

The graph platform developers use to achieve accurate GraphRAG for enterprise GenAI

FalkorDB delivers an accurate, multi-tenant RAG solution powered by a low-latency, scalable graph database technology. It is purpose-built for teams working with complex, interconnected data — structured or unstructured — in real-time and interactive environments, and it speaks OpenCypher with proprietary extensions that make graph traversal and querying practical in production.

Get started

Run FalkorDB locally, model your first graph, and query it in a few minutes.

Star us on GitHub

FalkorDB is open source. A star helps other developers find the project.

Try FalkorDB Cloud

Spin up a fully managed instance for free, with no local setup at all.

Build GraphRAG

Ground your GenAI application in a knowledge graph with the GraphRAG SDK.

Primary features

Property graph model

Nodes, relationships, labels, and properties, following the openCypher property graph model.

OpenCypher query language

Declarative pattern matching, plus proprietary extensions layered on top of OpenCypher.

Full-text, vector, and range indexes

RESP and Bolt protocols

Connect over the RESP protocol or over Bolt, whichever your stack already speaks.

Sparse matrix storage

Graphs are held as sparse adjacency matrices for compact storage and fast traversal.

GraphRAG built in

Turn unstructured sources into a knowledge graph and query it from your GenAI app.

Get Started

Launch an instance using Docker, or use FalkorDB Cloud

Ports Exposed

  • 6379 (FalkorDB Server)
    Use this port to connect via the CLI or any FalkorDB-compatible client.
  • 3000 (FalkorDB Browser)
    Access the FalkorDB web UI by opening your browser at: http://localhost:3000
Once loaded, you can interact with FalkorDB using any of the supported client libraries
📖 New to FalkorDB? Follow the step-by-step Getting Started guide for a complete walkthrough — from setup to modeling, loading, and querying your first graph.
Here we’ll use FalkorDB Python client to create a small graph representing a subset of motorcycle riders and teams taking part in the MotoGP league, once created we’ll start querying our data.
For additional demos please visit Demos.

Client libraries

Language-specific clients have been written by the community and the FalkorDB team. The full list and links can be found on the Client Libraries page.

Data import

When loading large graphs from CSV files, use the falkordb-bulk-loader:
See the Bulk Loader documentation for the full reference.

Community and support

Star FalkorDB

Star the repository to follow releases and help other developers discover the project.

Join the Discord

Ask questions and share what you are building with the team and the community.

Open a discussion

Propose ideas, report rough edges, and search past answers on the FalkorDB forum.

License

FalkorDB is licensed under the the Server Side Public License v1 (SSPLv1).

Frequently Asked Questions

FalkorDB is a high-performance graph database built as a Redis module. Unlike traditional graph databases, it uses a sparse adjacency matrix representation (based on GraphBLAS) for efficient storage and fast traversals. It supports OpenCypher queries, both RESP and Bolt protocols, and provides built-in GraphRAG capabilities for GenAI applications.
FalkorDB excels at use cases involving complex, interconnected data: social networks, recommendation engines, knowledge graphs, fraud detection, and GraphRAG for GenAI applications. Its low-latency design makes it ideal for real-time and interactive user environments.
The quickest way is Docker: docker run -p 6379:6379 -p 3000:3000 -it --rm falkordb/falkordb:latest. This starts the server and a browser UI at http://localhost:3000. Then install a client library and follow the Getting Started guide.
Yes. FalkorDB Cloud provides a fully managed, multi-tenant graph database service. You can create a free instance and skip local setup entirely.
FalkorDB uses OpenCypher with proprietary extensions. It supports full-text search, vector similarity search, and range indexing. See the Cypher documentation for the complete query language reference.