NVIDIA AI CKG
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
Open the source (opens github.com) https://github.com/yarmoluk/ckg-nvidia-ai
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.Yarmoluk.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
ckg-nvidia-ai@0.16.4
From the server's entry in the official MCP Registry
Remote endpoint (streamable-http)
https://ckg-nvidia-ai.onrender.com/mcp
From the server's entry in the official MCP Registry
Related
-
NVIDIA NemoClaw CKG
MCP serversNVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
ckg-nvidia-nemoclaw@0.10.3 -
ckg-nemotron-perplexity
MCP serversNVIDIA Nemotron + Perplexity Sonar as knowledge graphs — 2 domains, 83 nodes. MCP-native.
ckg-nemotron-perplexity@0.2.1 -
ckg-mcp
MCP servers97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.
ckg-mcp@0.7.9 -
Salesforce AgentForce CKG
MCP serversSalesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
ckg-agentforce@0.10.3 -
elements
MCP serversThe UI SDK and agent-ready developer toolkit for AI factories, robotics, and autonomous vehicles.
git clone https://github.com/NVIDIA/elements.git -
NVIDIA CUDA Docs
MCP serversSearch NVIDIA CUDA documentation and code samples from AI coding agents.