# FalkorDB/QueryWeaver

An open-source Text2SQL tool that transforms natural language into SQL using graph-powered schema understanding. Ask your database questions in plain English, QueryWeaver handles the weaving.

Repository: https://github.com/FalkorDB/QueryWeaver
Canonical: https://ross.abutalabs.com/products/queryweaver
Homepage: https://app.queryweaver.ai
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: falkordb, semantic-layer, text2sql
Last push: 2026-09-02T09:07:06+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 98, longevity 28
- inputs: {"age_days": 402, "days_push": 0, "days_rel": 15, "gap_med": 4, "n_releases_24m": 16}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1073, forks 133 (observed 2026-09-03T02:15:05.857075+00:00)

## What it is
QueryWeaver is an open-source Text2SQL tool that converts plain-English questions into SQL queries using graph-powered schema understanding. It is offered as a self-hostable FastAPI application (Docker or PyPI) with a REST API, MCP support, and a web UI, backed by multiple LLM providers.

## Use cases
- ask database questions in plain English
- convert natural language to SQL queries
- text-to-SQL for enterprise databases
- let non-technical users query a SQL database
- expose a database chat interface via MCP
- self-host a natural language SQL assistant

## When to choose
- you want an open-source, self-hostable Text2SQL service
- you need REST API or MCP access to natural-language SQL generation
- your schema is complex and benefits from graph-based schema understanding
- you want to use different LLM providers (OpenAI, Gemini, Anthropic, Azure)

## When to avoid
- you need a lightweight in-process library rather than a deployed service
- you cannot expose your database schema to an external LLM provider
- AGPL-3.0 licensing is incompatible with your usage
- you need guaranteed-correct SQL without LLM hallucination risk

## Facets
- artifact type: application
- maturity: active
- function: nlp, llm-inference, database, api-framework, mcp, rag
- domain: databases, large-language-models, developer-tools, self-hosted
- platform: python, self-hosted, cross-platform
- tags: text2sql, natural-language-to-sql, graph-schema, falkordb, semantic-layer, fastapi, sql-generation, natural-language-processing, docker, web-server

## Member repositories
- FalkorDB/QueryWeaver (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:05.857075+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:59.246483+00:00, confidence not recorded.
  - readme: https://github.com/FalkorDB/QueryWeaver (fetched 2026-09-03T02:15:05.857075+00:00, sha 573eb4b9a13c)
  - homepage: https://app.queryweaver.ai (fetched 2026-08-29T12:56:22.742761+00:00, sha 5f8dbf00b0f3)
  - registry_pypi: https://pypi.org/pypi/queryweaver/json (fetched 2026-08-29T12:56:22.745358+00:00, sha f083a54e9c9f)
- Data as of 2026-08-30T08:39:29.467469+00:00.