# auto-ontology: Ground Agent Queries in Enterprise Data with NVIDIA NIM This repository profile is provided by osrepos.com, an open source repository discovery platform. Source: osrepos.com Repository profile: https://osrepos.com/repo/nvidia-auto-ontology Generated for open source discovery and AI-assisted research. NVIDIA Auto Ontology builds a semantic context layer from enterprise metadata, helping agents generate more reliable, explainable data queries. It uses NVIDIA NIM for inference and exposes context through MCP, a CLI, and an API. GitHub: https://github.com/NVIDIA/auto-ontology OSRepos URL: https://osrepos.com/repo/nvidia-auto-ontology ## Summary NVIDIA Auto Ontology builds a semantic context layer from enterprise metadata, helping agents generate more reliable, explainable data queries. It uses NVIDIA NIM for inference and exposes context through MCP, a CLI, and an API. ## Topics - python - ai-agents - mcp - knowledge-graph - text-to-sql - semantic-layer - enterprise-data ## Repository Information Last analyzed by OSRepos: Mon Nov 02 2026 21:17:28 GMT+0000 (Western European Standard Time) Detail views: 4 GitHub clicks: 0 ## Safety Notice OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything. ## Content ## Overview NVIDIA Auto Ontology is a semantic, graph-based context layer for agents working with enterprise data. Built around NVIDIA NIM for inference, it turns metadata from connected data sources into an ontology that helps agents understand what metrics and entities mean, where they come from, and how they relate. The aim is to make agentic analytics more reliable than querying databases without business context. It complements existing semantic models and makes the resulting context available to agent harnesses through MCP, a CLI, and an API. The project includes a web application and supports local deployment with Docker Compose or deployment to Kubernetes. ## Key Features - Generates an ontology from enterprise metadata and connects existing ontologies and semantic models. - Reconciles differing definitions of business metrics and entities across systems. - Translates natural-language questions into SQL and executes queries against connected databases. - Checks generated queries against certified definitions and lineage, with provenance returned alongside answers. - Provides a web UI for chat, analysis, catalog management, analytics, and settings. - Offers authenticated API access, including user-scoped API tokens and streaming chat responses. - Exposes data context to agent harnesses through an MCP server. - Supports deployments with Docker Compose or a Kubernetes Helm chart. ## Use Cases - Data and analytics teams can let business users ask questions about metrics in natural language while grounding answers in catalog definitions. - Agent developers can connect MCP-compatible tools or applications to enterprise data with a shared semantic context layer. - Data stewards can reconcile definitions across sources and check query results against certified definitions and lineage. - Platform teams can deploy a self-hosted analytics application for connected databases, using Docker Compose for a local stack or Helm for Kubernetes. ## Our Take Auto Ontology is an active, fairly young project for teams that need a deployable semantic layer for agent-driven analytics and can operate its database, model endpoints, and application stack. **Good fit if:** - You need agents to query structured data using business definitions, relationships, and lineage rather than schema details alone. - Your team can provide NVIDIA NIM credentials or compatible inference endpoints and manage the required application services. - You want MCP, API, and web access to the same data context, and Apache-2.0 licensing fits your use. **Look elsewhere if:** - You need a project that accepts external contributions. The maintainers say contributions are not currently being accepted. - You need a lightweight library without a Postgres-backed application stack, Docker, or Kubernetes deployment needs. - You require published releases or evidence of test coverage before adoption. The project has no release in the past year, and the supplied project facts report no test suite. ## Project Health | Signal | Value | |---|---| | Status | **Active**: regular commits | | Last commit | 2026-11-01 (1 day ago) | | Commits, last 90 days | 100+ | | Releases, last 12 months | 0 | | Contributors | 12 (top contributor: 37% of commits) | | Issues closed, last 90 days | 0+ | | Pull requests merged, last 90 days | 93 (typically merged in 0 days) | | Project age | 6 months | Checked on 2026-11-02 with the GitHub API. ## Project Facts - Language: Python - License: Apache-2.0 - Stars: 738 - Forks: 90 - Archived: no ## What You Need Detected in the repository: - Python >=3.12,<3.14 (from pyproject.toml) - A Dockerfile, so it can run in a container; a Compose file sets up the related services - A Helm chart for Kubernetes - Automated checks on GitHub Actions ## Getting Started For a local Docker Compose setup, clone the repository, configure `.env` from `.env.example` with database and model credentials, then run: ```bash docker compose up -d --build ``` See the [README](https://github.com/NVIDIA/auto-ontology) and [deployment guide](https://github.com/NVIDIA/auto-ontology/blob/main/DEPLOYMENT.md) for configuration and Kubernetes instructions. ## License in Plain Words **Apache-2.0** (permissive). - Commercial use: yes - Modify and redistribute: yes - You must keep: the license, the NOTICE file and a note of your changes - Share your changes: no - Includes an explicit patent grant from the contributors A summary, not legal advice: the LICENSE file is what applies. ## Alternatives - [QueryWeaver](https://osrepos.com/repo/falkordb-queryweaver): QueryWeaver generates SQL from schema graphs for PostgreSQL and MySQL, while auto-ontology builds a broader semantic context layer for agents. - [vanna](https://osrepos.com/repo/vanna-ai-vanna): Vanna focuses on database chat interfaces that generate SQL and return results, while auto-ontology provides reusable enterprise context through MCP, a CLI, and an API. | Project | Language | License | Stars | Status | |---|---|---|---|---| | **auto-ontology** | Python | Apache-2.0 | 738 | Active | | [QueryWeaver](https://osrepos.com/repo/falkordb-queryweaver) | Python | AGPL-3.0 | 1.1k | Active | | [vanna](https://osrepos.com/repo/vanna-ai-vanna) | Python | MIT | 23.8k | Archived | ## Considerations - The local stack requires Docker and Docker Compose, plus Postgres and an NVIDIA API key for the default NVIDIA NIM setup. Kubernetes deployment is also supported; the documented Python runtime is 3.12 or 3.13. - UI-added database credentials are stored in plaintext in Postgres unless Vault is fully configured. Review the connection-management guidance and configure Vault if plaintext credential storage is unsuitable. - The repository is active, with regular recent commits and a dozen contributors, but it is still young and has no release in the past year. The measured contributor data does not indicate dependence on one person. - The project reports no test suite in the supplied project facts. It is also not accepting external contributions, which may affect teams that expect to contribute fixes upstream. - Apache-2.0 applies to the project; third-party components have separate notices. Runtime model APIs and connected data systems are subject to their own terms.