auto-ontology
Gives AI agents a clear map of what a company's data actually means (business terms mapped to tables and columns, not just column names), so agents stop guessing and give fewer confidently wrong answers to business questions.
View nvidia/auto-ontology on GitHub- GitHub stars
- 12,451
- Forks
- —
- Language
- Python
Project details
- Repository
- nvidia/auto-ontology
- Licence
- Apache-2.0
- Primary language
- Python
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
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.
Explore by topic
More tools in AI agents
- rea
morluto · MIT
Lets your AI coding agent reverse-engineer a feature you like in any app, explain exactly how it works with evidence, and rebuild a version of it for your own product,…
- skills
mattpocock · MIT
A free, open-source library of AI agent skills by well-known TypeScript educator Matt Pocock that fixes common coding-agent failure modes: skills like /grill-me get the…
- superpowers
obra · MIT
An open-source skills framework that gives coding agents a structured methodology (brainstorming, planning, subagent delegation) for shipping software reliably.
- ecc
affaan-m · MIT
An open-source performance layer for AI coding agents like Claude Code, Codex and Cursor, adding memory, skills and security so agents keep context and work more…