CKG-NVIDIA- AI - Nvidia Developer Stack As A Compressed Knowledge Graph - 20 Domains, 998 Nodes, Agents Traverse Type Dependency Graphs
About
NVIDIA AI developer stack as a Compressed Knowledge Graph (CKG) — 20 domains, 998 nodes, every prerequisite chain declared as typed edges. Agents traverse REQUIRES/ENABLES relationships instead of scanning docs. 4× F1 vs RAG, 11× fewer tokens. No API key required
Details
- Author
- Yarmoluk
- Downloads
- 256
- Categories
- AI, Other, Productivity, Knowledge Base
Jump to
- 4× F1 and 11× fewer tokens vs RAG
- 998 nodes across 20 NVIDIA AI domains
- Deterministic graph traversal – no hallucination
- Read-only: never writes, mutates, or executes
- Typed edges (REQUIRES, ENABLES, RELATES_TO, IMPLEMENTS)
- Three-state confidence (high, null, low) for every edge
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
CKG-NVIDIA- AI - Nvidia Developer Stack As A Compressed Knowledge Graph - 20 Domains, 998 Nodes, Agents Traverse Type Dependency GraphsCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install with pip install ckg-nvidia-ai and run the MCP server via uvx ckg-nvidia-ai. Configure it in Claude Desktop, Claude Code, Cursor, or other MCP clients using the provided JSON snippets. Tools include list_domains(), search_concepts(), query_ckg(), get_prerequisites(), and ask_nvidia() (the last requires Ollama with qwen2.5:14b).
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ckg-nvidia- ai - nvidia developer stack as a compressed knowledge graph - 20 domains, 998 nodes, agents traverse type dependency graphs": {
"nvidia-ai": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}
}McpServers
{
"nvidia-ai": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}NVIDIA AI Developer Stack as a Compressed Knowledge Graph
4× F1 · 11× fewer tokens · 998 nodes · deterministic traversal
Instead of scanning docs or re-inferring structure on every query, your agent traverses declared relationships. 20 NVIDIA AI domains, every prerequisite chain typed and ready.
Install:
uvx ckg-nvidia-ai
Example:
query_ckg("TensorRT-LLM", "nvidia-tensorrt-triton", depth=3)
Returns: CUDA Toolkit, FP8/FP4 Quantization, Hopper SM90 as hard prerequisites. Triton Inference Server and NIM Microservice Runtime as dependents. 269 tokens. No hallucination.
If an edge isn't declared, the traversal returns nothing rather than hallucinating a path. That silence is signal.
Tools: list_domains · query_ckg · get_prerequisites · search_concepts · ask_nvidia (Ollama, no API key)
Domains: NIM · NeMo · TensorRT · CUDA · Isaac · Cosmos · Omniverse · Riva · Jetson · DRIVE · Clara · Metropolis · GameWorks · HPC SDK · CUDA-X · Developer Tools · Graphics Research · AI Enterprise · Developer Ecosystem · OpenShell
Benchmark: CKG F1 0.471 vs RAG 0.123 · 269 tokens vs 2,982 per query
github.com/Yarmoluk/ckg-nvidia-ai
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
