FalkorDB Launches QueryWeaver, a Graph-powered Text-to-SQL Open-Source Tool

Tel Aviv, September 3, 2025 - FalkorDB today announced the launch of its Text-to-SQL open-source project 'QueryWeaver', designed to allow data analyst and enterprise developers to spend more time acting on their data than fetching it.

QueryWeaver uses a graph to create a semantic layer on top of the user's existing databases. When prompted with a complex query like, for example, "show me customers who bought product X in a certain 'REGION' over the last Y period of time," the tool knows which tables to join and how. When the user follows up with "just the ones from Europe," the tool remembers what the user was talking about.

Instead of feeding a large language model (LLM) a list of tables and columns, QueryWeaver feeds it a knowledge graph that understands what a customer is, how it connects to orders, which products belong to a campaign, and what "active user" actually means in the user's business context. This pushes the goalpost in Enterprise use cases where multiple databases, with many schemas, need to be queried to fetch the information an analyst may be looking for.

QueryWeaver aims to generate high-accuracy, ready-to-use SQL queries from natural language, dramatically reducing the query-writing time and serving as a go-to tool for data analysts who previously could not load their schemas into an LLM due to context constraints.

Launched with an API and MCP, QueryWeaver is available to all for testing.
Official GitHub Repository: https://github.com/FalkorDB/QueryWeaver

Dan Shalev, Marketing & Product
dan.shalev@falkordb.com
(972)51 558 4042
FalkorDB Inc., 850 New Burton Road, Suite 201 City of Dover, Country of Kent Delaware 199404

FalkorDB is a next-generation graph database designed to optimize large language models (LLMs) through its unique GraphRAG technology. Founded by ex-Redis engineers, it uses sparse matrices and GraphBLAS for efficient graph traversal and algebraic querying. FalkorDB supports vector similarity search and integrates seamlessly with AI frameworks like LangChain and LlamaIndex. Its ultra-low-latency architecture enables real-time decision-making by combining knowledge graphs with vector databases, reducing hallucinations in AI outputs. Additionally, FalkorDB offers multi-tenant capabilities and supports the Bolt protocol for easy migration from Neo4j. This makes it ideal for CTOs, Chief Architects, and AI/ML Engineers who need scalable solutions for high-performance Retrieval-Augmented Generation (RAG) applications. With its distributed architecture and in-memory processing, FalkorDB ensures fast query execution even with massive datasets, making it a preferred choice for enterprise-scale AI deployments.

This release was published on openPR.