# nvidia/auto-ontology

> auto-ontology is an open library that builds a context layer from enterprise metadata so AI agents know where data lives, what it means and whether to trust it. It generates an ontology of business terms, SQL attributes and table relationships from connected databases, and people certify that ontology before agents rely on it. The core code is written in Python, with a Next.js web frontend.

Source: https://github.com/nvidia/auto-ontology
Indexed: commit 22e22c8 on 2026-11-14 by Repowise. Facts come from the source and git history, not from the maintainer.

## Facts

- Type: App
- Language: Python
- Stars: 12,748 at index time
- License: Apache-2.0
- Code health: 7.0/10, Fair
- Last commit: 2026-11-13
- Contributors: 13

## Install

From the README: https://github.com/nvidia/auto-ontology#quickstart

Clone the auto-ontology repository.
    git clone https://github.com/nvidia/auto-ontology.git

Move into the auto-ontology folder.
    cd auto-ontology

Copy the example environment file to .env, then set the API key, passwords and admin credentials in it.
    cp .env.example .env

Start Postgres.
    docker compose up -d --wait postgres

Build and start the rest of the stack, then sign in with the admin credentials from .env.
    docker compose up -d --build

## How it works

Source databases are read by the ingestion service, whose entry point is auto_ontology/ingestion_service/__main__.py, which extracts schemas, profiles columns and samples values into the catalog. The auto_ontology/catalog module records each database's structure and the SQL run against it as nodes and edges in a graph store. The auto_ontology/dal module holds every database query behind the catalog, the glossary of Terms, tags and the exploration graph. The generated ontology is stored in Postgres with embeddings in pgvector for retrieval, and alembic keeps the schema migration history that moves that database from one revision to the next. The frontend directory is the Next.js web app where people chat with the data, browse the catalog and refine terms.

- auto_ontology/ingestion_service/__main__.py: entry point
- auto_ontology/retrieval/entity_coverage/main.py: entry point
- auto_ontology/retrieval/text_to_sql/main.py: entry point
- auto_ontology/semantic/__main__.py: entry point
- auto_ontology/server/__main__.py: entry point
Modules: auto_ontology, frontend, mcp, alembic, dev_tools, root. 995 files, 134,289 lines, 8,271 symbols.

## Code health

- Score: 7.0/10 (Fair)
- Trend: 6.9 on 2026-11-05, 6.9 on 2026-11-10, 7.0 on 2026-11-14
- Rank: #122 of 4,000+ indexed repos
- Hotspots: frontend/components/termsPage/TermsView.tsx, auto_ontology/dal/terms.py, frontend/common/SinglePageComposer.tsx, auto_ontology/semantic/visit_enter.py, frontend/components/explorationPage/ExplorationView.tsx
- Lowest file: auto_ontology/semantic/visit_enter.py
- Dead code: 37 findings

## Maintenance

- Last commit 2026-11-13, first commit 2026-04-06, 1,114 commits
- 13 contributors, bus factor 2

## Security

- Security findings are shown to signed-in users at https://repowise.dev/repo/nvidia/auto-ontology/security

## More

- Page: https://repowise.dev/repo/nvidia/auto-ontology
- Ask this codebase: https://repowise.dev/repo/nvidia/auto-ontology/chat
- Docs: https://repowise.dev/repo/nvidia/auto-ontology/docs
- MCP (signs in with Repowise on first use):
    claude mcp add --transport http repowise https://api.repowise.dev/mcp/nvidia/auto-ontology