NVIDIA releases Auto Ontology open semantic layer for AI agents
Original title: NVIDIA Releases Auto Ontology: An Open Semantic Layer That Grounds AI Agent SQL
NVIDIA released Auto Ontology, an Apache 2.0 library that creates context layers from enterprise metadata to ground AI agents in certified business definitions.
Auto Ontology builds a semantic layer from metadata sources including Databricks, Postgres, Snowflake and DuckDB. Agents query it through MCP, CLI and API tools using certified definitions and lineage. NVIDIA reports 90 percent faster ontology creation in internal testing. The library ships with evaluation harness for text-to-SQL benchmarks but no public accuracy scores.
Unconfirmed: No published text-to-SQL accuracy scores available for independent verification
- Context layer reduces ontology creation time 90 percent
- Agents query via 9 read-only MCP tools
- Default LLM is Nemotron via NVIDIA NIM
- OpenAPI spec publishes 87 operations
- Runs on Docker Compose or Kubernetes Helm chart
- Vendors
- NVIDIA
- Products
- Auto Ontology
From the original article
7 min read at marktechpost.comNVIDIA released Auto Ontology, an Apache 2. 0 library that generates a semantic layer from enterprise metadata. It grounds agent SQL in certified definitions and serves context through MCP, CLI and API.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.