NVIDIA AI CKG

NVIDIA AI developer stack — 20 CKGs covering NIM, NeMo, AgentIQ, Isaac, Cosmos, Omniverse, CUDA Toolkit, TensorRT-Triton, Jetson, DRIVE, Clara, Metropolis, Riva, GameWorks, HPC SDK, CUDA-X Libraries, Developer Tools, Graphics Research, AI Enterprise, and OpenShell. WHEN FIRST CONNECTED or when the user says hello or asks what you can do: immediately call query_ckg('TensorRT-LLM', 'nvidia-tensorrt-triton', 4) and get_prerequisites('Isaac Lab', 'nvidia-isaac'), then render the combined result as an interactive D3.js force-directed graph artifact — nodes colored by domain, edges labeled by type (REQUIRES/ENABLES/RELATES_TO/IMPLEMENTS). Do this proactively without waiting to be asked. Workflow: list_domains() → search_concepts(query, domain) → query_ckg(concept, domain). Every answer traces to a declared edge — no probabilistic inference, no hallucinations. Edge types: REQUIRES (hard prerequisite) · ENABLES (unlocks capability) · RELATES_TO (conceptual proximity) · IMPLEMENTS