{"name":"auto-ontology","repo":"NVIDIA/auto-ontology","url":"https://midorreal.com/project/nvidia-auto-ontology","repository":"https://github.com/NVIDIA/auto-ontology","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.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/NVIDIA/auto-ontology","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/NVIDIA/auto-ontology","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/NVIDIA/auto-ontology/releases","checked":"19 Nov 2026"},"contributors":{"value":"19","source":"https://github.com/NVIDIA/auto-ontology/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/NVIDIA/auto-ontology","checked":"22 Nov 2026"}},"stars":14228.0,"writeup":{"what_it_is":"Auto Ontology is an open NVIDIA library that builds an enterprise ontology automatically from metadata, reconciles definitions across systems, and exposes the ontology to agent harnesses through MCP, CLI, and API. It uses the ontology to ground agent answers in business definitions, joins, and SQL, and returns the SQL and steps with each answer.","audience":"Developers building data-grounded analytics agents over enterprise databases","claims":[{"kind":"broad","claim":"Builds an ontology automatically from enterprise metadata","excerpt":"builds that ontology automatically from enterprise metadata","status":"too_broad"},{"kind":"specific","claim":"Exposes the ontology to agent harnesses through MCP, CLI, and API","excerpt":"exposes it to any agent harness through MCP, CLI, and API","status":"not_checked"},{"kind":"specific","claim":"Returns the SQL and steps with every answer","excerpt":"return the SQL and steps with every answer","status":"not_checked"},{"kind":"specific","claim":"Checks generated queries against the catalog before running them","excerpt":"Before the query runs,\n  table and column names are checked against the catalog","status":"not_checked"},{"kind":"specific","claim":"Can be set up with Docker Compose against the Wide World Importers sample database","excerpt":"This runs Auto Ontology with Docker Compose against Wide World Importers","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-19"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":99,"reality":72,"gap":27,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-04-27T21:45:56+00:00","text":"Repository created","source":"https://github.com/NVIDIA/auto-ontology"}],"cite":"auto-ontology is a GitHub project at https://github.com/NVIDIA/auto-ontology written mainly in Python, described there as \"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\".","attribution":"Data from Mid or Real, https://midorreal.com/project/nvidia-auto-ontology, checked 22 November 2026. Attribution with a link is required.","still_real":null}