{"name":"io.github.Yarmoluk/ckg-nvidia-nemoclaw","slug":"yarmoluk-ckg-nvidia-nemoclaw","title":"NVIDIA NemoClaw CKG","description":"NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.","url":"https://mcp.market/server/yarmoluk-ckg-nvidia-nemoclaw","rating":null,"grade":"B","score":75,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":15,"stars":null,"forks":null,"downloads_week":107,"last_push_at":null,"license":"MIT"},"uptime":{"percent":100,"checks":28,"ok":28,"last_checked_at":"2026-09-27T16:11:29.523Z","last_ok_at":"2026-09-27T16:11:29.523Z","latency_ms":391},"claimed":false,"transport":"mixed","callable_via_gateway":true,"default_price_micros":0,"repository":"https://github.com/Yarmoluk/ckg-nvidia-nemoclaw","website":null,"version":"0.10.3","remotes":[{"type":"streamable-http","url":"https://ckg-nvidia-nemoclaw.onrender.com/mcp"}],"packages":[{"registryType":"pypi","identifier":"ckg-nvidia-nemoclaw","version":"0.10.3","runtimeHint":"uvx","transport":{"type":"stdio"}}],"tools":[{"name":"ask_nemoclaw","description":"Answer a question about NVIDIA NemoClaw by traversing the knowledge graph.\n\nCovers: agent runtimes (OpenClaw/Hermes/Deep Agents), OpenShell platform,\ninference routing, network policy, security layers, deployment paths,\nprogressive tool disclosure, managed MCP servers, snapshots, shields,\nFOX Blueprint, Nemotron 3 Ultra ecosystem, and platform support.\n\nArgs:\n    question: Your question about NemoClaw concepts or architecture.\n","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"question":{"title":"Question","type":"string"}},"required":["question"],"title":"ask_nemoclawArguments"}},{"name":"get_prerequisites","description":"Return the full upstream prerequisite chain for a NemoClaw concept.\n\nUseful for understanding what a concept depends on end-to-end.\n\nArgs:\n    concept: Exact or partial concept label.\n","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"concept":{"title":"Concept","type":"string"}},"required":["concept"],"title":"get_prerequisitesArguments"}},{"name":"list_domains","description":"List available domains in this CKG server.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{},"title":"list_domainsArguments"}},{"name":"query_ckg","description":"Return the typed subgraph around a NemoClaw concept.\n\nArgs:\n    concept: Exact or partial concept label (e.g. 'OpenClaw', 'NetworkPolicy', 'L7Proxy').\n    depth: Traversal hops (1–5, default 3).\n","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"concept":{"title":"Concept","type":"string"},"depth":{"default":3,"title":"Depth","type":"integer"}},"required":["concept"],"title":"query_ckgArguments"}},{"name":"query_intersect","description":"Answer a conjunctive query: concepts reachable from EVERY anchor at once (A AND B).\n\nquery_ckg walks outward from one concept. This intersects the reachable sets of two or\nmore, which is the shape of most real questions — \"the component that satisfies A AND\napplies to B\". Neither anchor alone answers it; the answer lives in the overlap.\n\nEvery branch is an exact set of declared edges, so the intersection is exact. A concept\nappears only if a declared path reaches it from each anchor. A relation missing from the\ngraph produces an empty result, never a guess.\n\nArgs:\n    branches: Two or more branches. Either a bare anchor (\"TensorRT-LLM\"), which takes\n        everything within `depth` hops, or an anchor plus an explicit relation path using\n        '>' (\"TensorRT-LLM > REQUIRES > ENABLES\"), where each relation replaces the\n        frontier. '*' matches any relation. Mix both forms freely.\n    depth: Hops for bare-anchor branches, 1-5 (default 2). Ignored for explicit paths.\n    direction: 'out' follows dependencies, 'in' follows them backwards, 'both' (default).\n    mode: 'AND' (default) intersects branches; 'OR' unions them.\n    limit: Max concepts listed, 1-200 (default 40). The true count is always shown.\n\nReturns:\n    Markdown with the query plan and its per-step set sizes, then the answer set with\n    taxonomy tags. Reports which branch was empty when the intersection is empty.\n","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"branches":{"items":{"type":"string"},"title":"Branches","type":"array"},"depth":{"default":2,"title":"Depth","type":"integer"},"direction":{"default":"both","title":"Direction","type":"string"},"mode":{"default":"AND","title":"Mode","type":"string"},"limit":{"default":40,"title":"Limit","type":"integer"}},"required":["branches"],"title":"query_intersectArguments"}},{"name":"route_query","description":"Route a NemoClaw question to the optimal model and reasoning approach via graph depth.\n\nThe CKG graph IS the router. NemoClaw's dependency chains (e.g. OpenShell → L7Proxy →\nCorporateCA → mTLS) are deep and typed — hop depth is a deterministic complexity signal.\nNo heuristic: the graph decides which model and reasoning approach to use.\n\nRouting table:\n  hop_depth 1  → haiku  · direct          (single concept lookup)\n  hop_depth 2  → sonnet · generic_cot     (moderate chain)\n  hop_depth 3+ → opus   · sparql_cot      (deep chain, structured reasoning required)\n\nArgs:\n    question: Concept name or natural language question about NemoClaw / OpenShell.\n\nReturns:\n    model_tier + reasoning_approach + why + context subgraph to inject before LLM call.\n","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"question":{"title":"Question","type":"string"}},"required":["question"],"title":"route_queryArguments"}},{"name":"search_concepts","description":"Fuzzy search for NemoClaw concepts by name or keyword.\n\nArgs:\n    query: Partial name or keyword (e.g. 'policy', 'inference', 'agent').\n","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"title":"search_conceptsArguments"}},{"name":"verify_source","description":"Return the authoritative source URL and content hash for a NemoClaw concept node.\n\nEvery node in the CKG was declared from a specific source document. This tool\nreturns the source URL (where the node came from) and the SHA-256 hash of that\ndocument's bytes at extraction time. A hash mismatch on re-fetch means either\nthe source has changed (stale edge — re-extract) or the graph was patched without\nre-fetching (silent edit — investigate).\n\nAudit chain:\n    edge answer → graph commit → source_hash → source_url (fetch hint)\n\nVerification:\n    curl -s <source_url> | sha256sum\n    # compare output to source_hash\n\nArgs:\n    concept: Exact or partial concept label (e.g. 'CorporateCA', 'L7Proxy').\n","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"concept":{"title":"Concept","type":"string"}},"required":["concept"],"title":"verify_sourceArguments"}}],"scan":{"score":75,"grade":"B","scanned_at":"2026-09-24T17:25:14.915Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-24T17:25:14.855Z","components":{"code":{"score":25,"max":25,"notes":["13 source files scanned"]},"reliability":{"score":20,"max":20,"notes":["remote reachable in 679ms"]},"poisoning":{"score":15,"max":15,"notes":["8 tool descriptions checked"]},"auth":{"score":10,"max":15,"notes":["open endpoint, read-only tools"]},"maintenance":{"score":3,"max":15,"notes":["repository not readable: repo not found"]},"identity":{"score":2,"max":10,"notes":["no repository or website to verify"]}},"findings":[],"inputs":{"probes":[{"url":"https://ckg-nvidia-nemoclaw.onrender.com/mcp","reachable":true,"authRequired":false,"latencyMs":679,"serverInfo":{"name":"ckg-nvidia-nemoclaw","version":"1.30.0"}}],"packages":[{"registryType":"pypi","identifier":"ckg-nvidia-nemoclaw","version":"0.10.3","found":true,"weeklyDownloads":107,"license":"MIT","dependencyCount":7,"publishedAt":"2026-07-29T16:57:10.407245Z","repositoryUrl":"https://graphifymd.com"}],"repo":{"found":false,"owner":"Yarmoluk","repo":"ckg-nvidia-nemoclaw","error":"repo not found"},"icon":{"url":null,"source":"none"},"presence":{"stars":null,"forks":null,"downloadsWeek":107,"license":"MIT","lastPushAt":null,"score":15}}}},"grade_history":[],"reviews":[]}