io.github.Yarmoluk/ckg-nvidia-nemoclaw · v0.10.3 · docs-and-knowledge
NVIDIA NemoClaw CKG is healthy: it completed an MCP handshake in 1163 ms and exposes 8 tools.
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp (streamable-http)
Repository · JSON · Add to my inventory
| Users (last 30 days) | 0 |
| Handshake | Healthy |
| Auth needed | None |
| Tool count | 8 |
| Latency | 1163 ms |
| Last checked (UTC) | 2026-10-16T06:20:17.751Z |
| Checked (UTC) | Status | Latency | Error |
|---|---|---|---|
| 2026-10-16T06:20:17.751Z | Healthy | 1163 | |
| 2026-10-15T02:35:50.138Z | Healthy | 4373 |
ask_nemoclaw | Answer a question about NVIDIA NemoClaw by traversing the knowledge graph. Covers: agent runtimes (OpenClaw/Hermes/Deep Agents), OpenShell platform, inference routing, network policy, security layers, deployment paths, progressive tool disclosure, managed MCP servers, snapshots, shields, FOX Bluepr |
query_ckg | Return the typed subgraph around a NemoClaw concept. Args: concept: Exact or partial concept label (e.g. 'OpenClaw', 'NetworkPolicy', 'L7Proxy'). depth: Traversal hops (1–5, default 3). |
get_prerequisites | Return the full upstream prerequisite chain for a NemoClaw concept. Useful for understanding what a concept depends on end-to-end. Args: concept: Exact or partial concept label. |
search_concepts | Fuzzy search for NemoClaw concepts by name or keyword. Args: query: Partial name or keyword (e.g. 'policy', 'inference', 'agent'). |
list_domains | List available domains in this CKG server. |
verify_source | Return the authoritative source URL and content hash for a NemoClaw concept node. Every node in the CKG was declared from a specific source document. This tool returns the source URL (where the node came from) and the SHA-256 hash of that document's bytes at extraction time. A hash mismatch on re-f |
route_query | Route a NemoClaw question to the optimal model and reasoning approach via graph depth. The CKG graph IS the router. NemoClaw's dependency chains (e.g. OpenShell → L7Proxy → CorporateCA → mTLS) are deep and typed — hop depth is a deterministic complexity signal. No heuristic: the graph decides which |
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 anchor alone answer |