NVIDIA/auto-ontology

★533Python🇺🇸 North AmericaApache-2.0⑂ 67Issue 22Updated Oct 29, 2026

View on GitHub ↗

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.

NVIDIA builds a trust layer so agents stop guessing at metrics — Auto Ontology generates enterprise ontologies from metadata, reconciles conflicting definitions across systems, and validates agent-generated SQL against certified lineage before returning answers. It exposes this context via MCP, CLI, and API, making it useful for teams building reliable text-to-SQL or analytics agents rather than fast-but-wrong ones.

Metrics

Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.

Star growth and Trending appearances (last 30 days)

Created Apr 28, 2026 · First on trending Oct 28, 2026

Other notable repositories in the same category (AI agents)

• 47thtechcorner/RayCodes_AIJobSearchA local career agent that hunts jobs and shields against prompt injection
• JetBrains/thinkrailJetBrains' new agentic IDE turns the pi coding agent into isolated worktree workspaces
• nightly-labs/openbotA Desktop Hub That Gives Codex, Claude and Grok Their Own Workspaces
• elayadesign/ai-design-skillsMarkdown skill packs that teach AI coding tools to design pages
• makecindy/cindyA local AI agent that combines harnesses like Claude Code and Codex

See all AI agents repositories →