Weekly digestOne email a week: top 5 new tools + trending stars. Unsubscribe anytime.

Auto Ontology

NVIDIA/auto-ontology
Open source (free)
Needs setup You need your own server plus database, environment variables, domain or mail configuration. Read the official deployment docs first.

A Python framework for developers building semantic graph reasoning layers over data, enabling deterministic queries and clearer LLM context. 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.

Auto Ontology repository card

Pricing

Open source (free)

Update history

Last updated 2026-11-22;Listed 2026-11-11

Author

NVIDIA

More from this author

Trust info

Listed on 2026-11-11; Last updated 2026-11-22; Data synced on 2026-11-22

Trial feedback

Like it? Vote to help it rank higher.

Deploy command

docker compose up -d --wait postgres
   git clone https://github.com/NVIDIA/auto-ontology-eval.git ../auto-ontology-eval
   (cd ../auto-ontology-eval && uv sync && cp .env.example .env && \
     POSTGRES_PASSWORD='<the same password>' \
     uv run python scripts/seed/seed_wwi.py --database-name wideworldimporters --drop)

Taken from the project README. You need a server with Docker; you may still need to add environment variables.

From the README

Auto Ontology uses NVIDIA NIM endpoints for inference — either the hosted NVIDIA API catalog (integrate.api.nvidia.com) or self-hosted NIMs. The defaults in .env.example are:

Stars
★ 14.2k
Category rank
#349
Language
Python
License
Apache-2.0
Last updated
2026-11-22
Category
Developer tools
Section
General