auto-ontology

auto-ontologyLink to this section

auto-ontology is a RAG toolkit - Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for LLM and agent workflows.

OverviewLink to this section

Agents can retrieve documents and query databases, but reliability gates agentic analytics: a revenue metric answered faster is worth nothing if the number is wrong. Agents need a context layer that tells them where data lives, what it means, whether to use it, how to use it, where it came from, and what is similar. NVIDIA Auto Ontology is an open library that builds that layer from enterprise metadata, reconciles definitions across systems, and exposes it to any agent harness through MCP, CLI, and API. It complements the semantic models customers already own.

• Discover: generate enterprise ontologies from metadata; connect existing ontologies and semantic models; build AI-ready knowledge graphs. - Ground: give agents trusted business meaning for metrics, entities, and relationships; reconcile inconsistent definitions across systems. - Validate: check generated queries against certified definitions and lineage; return provenance with every answer. - Expose: serve context to any agent harness through MCP, CLI, and API. Learn: fold certified corrections and usage back into the ontology, so shared context improves with every question.

To run a text-to-SQL benchmark such as BIRD, refer to the ontology SQL evaluation repository.

auto-ontology is open-source, written primarily in Python, with 11,939 GitHub stars under the Apache 2.0 license. It was last updated on 2026-11-11.

Key capabilitiesLink to this section

From the project's documentation:

• Validate: check generated queries against certified definitions and lineage; return provenance with every answer.
• Expose: serve context to any agent harness through MCP, CLI, and API.
• Natural-language querying of structured data — questions are translated to
• Semantic catalog / ontology layer over relational sources, stored in
• Authentication & RBAC —using Better Auth.
• Web UI for chat, analysis, data catalog, analytics, and settings.

How it fits a local-AI stackLink to this section

auto-ontology runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related RAG toolkits in the directory:

• AnythingLLM
• Dify
• Haystack
• Khoj

SourcesLink to this section

• Source code & docs: NVIDIA/auto-ontology

Stats from GitHub, 2026-11-12.