Radar / AI infrastructure / NVIDIA Auto Ontology
NVIDIA Auto Ontology
Apache-2.0 framework that builds a semantic, graph-based layer over enterprise databases from metadata, then serves certified metric definitions to AI agents via MCP, CLI and API so they stop inventing your revenue number.
Why it matters
NVIDIA's answer to the biggest enterprise-agent failure mode — agents guessing SQL semantics from column names: it auto-generates an ontology, stores it in Postgres + pgvector, and exposes it through 9 read-only MCP tools, claiming 90% faster ontology creation in its own testing.
What you could build with it
A data consultancy could build a 'semantic layer as a service' for mid-size companies, generating certified metric definitions from their warehouse metadata so every AI analyst tool in the company answers revenue and churn questions from the same approved numbers.
Does it hold up?
Early but real: a full-stack system (FastAPI, Postgres/pgvector, Helm, connectors for Snowflake, Databricks, Trino and more) that reviewers cloned and ran, but it needs an NVIDIA API key, accepts no outside contributions yet, and publishes no text-to-SQL accuracy scores.
Learn more
First spotted on github: source.
More AI infrastructure
colibri: run 744B-parameter MoE models on consumer hardwarePure-C inference engine with zero dependencies that streams MoE experts from NVMe disk, keeping hot experts on GPU…infra · JEV 0.78claude-mem: persistent memory plugin that lets coding agents pick up where the last session left offPlugin that hooks five Claude Code lifecycle events, compresses session activity into a local SQLite + Chroma store…infra · JEV 0.74FreeToken: datacenter-scale MoE serving on desktop GPUsAn edge-native mixture-of-experts serving engine from UC Berkeley researchers that runs 290B+ parameter MoE models on…infra · JEV 0.74TorchTPU: Google's native PyTorch stack for TPUs, now open sourceAnnounced at PyTorch Conference 2026 on October 20: Google open-sourced TorchTPU, its native PyTorch backend for Cloud…infra · JEV 0.66Mesh-LLM: pool GPUs across machines behind one OpenAI-compatible endpointRust project that splits large models across machines into layer stages, fetches model shards by package, and serves…infra · JEV 0.64DeepInfer: DeepSeek's open-source production inference engineDeepSeek open-sourced DeepInfer, the high-performance inference framework powering its production services (155…infra · JEV 0.6
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.