QueryWeaver vs auto-ontology
Natural-language data querying projects compared
QueryWeaver and auto-ontology both turn natural-language questions into SQL and provide ways to connect agents or applications to data. QueryWeaver focuses on graph-based database schema context for PostgreSQL and MySQL, while auto-ontology builds a semantic context layer from enterprise metadata and existing models.
QueryWeaver: Turn Natural-Language Questions into SQL
QueryWeaver converts plain-English questions into SQL by using a graph representation of database schemas. It suits teams that want a self-hosted Text2SQL web app, REST API, MCP interface, or Python SDK for PostgreSQL and MySQL.
auto-ontology: Ground Agent Queries in Enterprise Data with NVIDIA NIM
NVIDIA Auto Ontology builds a semantic context layer from enterprise metadata, helping agents generate more reliable, explainable data queries. It uses NVIDIA NIM for inference and exposes context through MCP, a CLI, and an API.
| QueryWeaver | auto-ontology | |
|---|---|---|
| Language | Python | Python |
| License | AGPL-3.0 | Apache-2.0 |
| Stars | 1.1k | 738 |
| Forks | 135 | 90 |
| Last analyzed | Oct 3, 2026 | Nov 2, 2026 |
Key differences
- QueryWeaver builds graph-based schema context from PostgreSQL and MySQL; auto-ontology generates an ontology from enterprise metadata and can connect existing ontologies and semantic models.
- auto-ontology checks queries against certified definitions and lineage and returns provenance; QueryWeaver supports multi-turn queries and requires confirmation before destructive SQL execution.
- QueryWeaver offers a Python SDK, REST API, web app, and MCP-compatible HTTP surface; auto-ontology exposes context through an MCP server, CLI, API, and web app.
- QueryWeaver is licensed under AGPL-3.0, while auto-ontology is licensed under Apache-2.0.
- QueryWeaver requires FalkorDB and an LLM provider configuration; auto-ontology's default local setup uses Docker Compose, Postgres, and an NVIDIA API key, with Kubernetes deployment also supported.
- The supplied project facts list QueryWeaver with 1.1k stars and 135 forks, and auto-ontology with 738 stars and 90 forks.
Choose QueryWeaver if you…
- want a Text2SQL web app or Python SDK for PostgreSQL and MySQL.
- need REST or MCP integration options, including streaming chat responses.
- want to use multiple LLM providers, including Ollama, Gemini, or Anthropic.
Choose auto-ontology if you…
- need enterprise metadata, semantic models, and business definitions to ground agent queries.
- want query checks against certified definitions and lineage, with provenance alongside answers.
- plan to deploy with Docker Compose or Kubernetes and use NVIDIA NIM for inference.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.