bots.st/nvidia-ai-ckg
NVIDIA AI CKG
Answer questions and traverse knowledge graph
2121 ms
answered our call
- State
- Answered
- Protocol
- MCP 2025-06-18
- Tools listed
- 9
- Answered
- 3 of the last 3 calls
How to reach it
- MCP, HTTP
https://ckg-nvidia-ai.onrender.com/mcp - PyPI
uvx ckg-nvidia-aiReleased 4 Nov 2026, version 0.24.2
What it can do
| Tool | What it says it does |
|---|---|
ask_nvidia | Ask a natural-language question answered by Qwen grounded on the NVIDIA CKG. Requires Ollama running locally with a Qwen model pulled: ollama pull qwen2.5:14b Override model: NVIDIA_CKG_MODEL env var (default: qwen2.5:14b) Override host: NVIDIA_CKG_OLLAMA env var… |
get_prerequisites | Return the full ordered prerequisite chain for a concept — everything to learn first. Args: concept: Target concept — e.g. 'Speculative Decoding', 'Isaac Lab', 'NeMo Guardrails'. domain: Domain name from list_domains(). |
list_domains | List all 21 NVIDIA AI domains available in this knowledge graph. |
list_ecosystem | Discover other CKG packages for adjacent domains — finance, healthcare, legal, and more. |
query_ckg | Traverse the NVIDIA knowledge graph from a concept — prerequisites and dependents. Args: concept: Concept name (partial match supported) — e.g. 'TensorRT', 'NIM', 'Isaac Lab'. domain: Domain name from list_domains() — e.g. 'nvidia-tensorrt-triton', 'nvidia-isaac'… |
query_intersect | Answer a conjunctive query: concepts reachable from EVERY anchor at once (A AND B). query_ckg walks outward from one concept. This intersects the reachable sets of two or more, which is the shape of most real questions — "the component that satisfies A AND applies to B". Neither… |
route_query | Route an NVIDIA AI question to the optimal model and reasoning approach via graph depth. The CKG graph IS the router — hop depth is a deterministic complexity metric. Deeper NVIDIA prerequisite chains (CUDA → TensorRT → TensorRT-LLM → NIM) require more capable models. No heuristic… |
search_concepts | Find concepts in a NVIDIA AI domain by keyword. Args: query: Search term — e.g. 'inference', 'sandbox', 'quantization', 'guardrails'. domain: Domain name from list_domains() — e.g. 'nvidia-nim', 'nvidia-openshell'. |
verify_source | Return the source URL and SHA-256 content hash for any NVIDIA AI concept node. Audit chain: edge answer → graph commit → source_content_hash → source_url (fetch hint). Verification: curl -s <source_url> | sha256sum # compare to source_hash Args: concept: Concept label… |
In its maker's words
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
- Source
- github.com/Yarmoluk/ckg-nvidia-ai
- Publisher
- Yarmoluk (5 listings in the registry)
- Listed from
- the official MCP Registry as
io.github.Yarmoluk/ckg-nvidia-ai - Version
- 0.16.4, updated 29 Jul 2026
- Kinds of work
- AI models and agent tools, Search and research, Documents and files
Every call we made
| When | What happened | Time |
|---|---|---|
| Answered | 2121 ms | |
| Answered | 1517 ms | |
| Answered | 994 ms |
Next door
- WhiteMagic — governed local memory for agent continuityGoverned local agent memory reads and writes
- PolyrankTrader metrics, rankings, and strategy backtests
- DiffCIValidate DiffCI reports and plan affected tests
- FOGA nodeResolve agent identities and safety verdicts, simulate and r
- Mind Upload AI meta harnessRoute coding work through saved memories
Is this your bot? Claim its address to add a verified badge and keep the listing current.