NVIDIA/auto-ontology
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
- 3.0kstars
- 244forks
- 23open issues
- updated today
About auto-ontology
auto-ontology is a free, open-source AI developer tool by NVIDIA, written mainly in Python. 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. It has 3.0k GitHub stars and 244 forks, and was last updated today. It's released under the Apache-2.0 license, a standard open-source license.
Similar free tools
langchain149k stars · The agent engineering platform.
promptfoo27k stars · Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line
opik23k stars · Monitor and evaluate LLM applications and AI agents with comprehensive tracing and dashboards.
open-agent-sdk-typescript2.7k stars · Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source
AdalFlow4.2k stars · Build and optimize LLM applications with auto-prompting and agent frameworks.
llm-gateway7.6k stars · Open Source LLM Gateway 🦚
Discussions
- Blueskythegabriel.eu · todayGitHub - NVIDIA/auto-ontology: Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, a...0 likes00
- Blueskynigolv.bsky.social · todayGitHub - NVIDIA/auto-ontology: 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.0 likes00
- Hacker Newscampervans · todayNvidia – open-source auto-ontology263 points127
- Blueskyshadowfetchstudio.bsky.social · 1d agoGitHub - NVIDIA/auto-ontology: 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.4 likes00
auto-ontology FAQ
Can I use auto-ontology commercially?
Yes. Apache-2.0 is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.
Is auto-ontology free?
Yes. auto-ontology is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does auto-ontology run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does auto-ontology need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is auto-ontology still maintained?
Yes. It was last updated today and has 23 open issues on GitHub.
How hard is auto-ontology to set up?
Medium: typically about 30 min, using Docker. The project's install command is: docker compose up -d --wait postgres
What are alternatives to auto-ontology?
Similar free, open-source tools include langchain, promptfoo, opik, open-agent-sdk-typescript.
Related topics
Maintain auto-ontology? Add a FreeAIRepo badge to your README
[](https://www.freeairepo.com/repo/NVIDIA/auto-ontology)