# NVIDIA NemoClaw CKG

> NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.

- name: io.github.Yarmoluk/ckg-nvidia-nemoclaw
- version: 0.10.3
- connection class: R0 (autonomous)
- trust: 91/100
- quality: 76/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Yarmoluk%2Fckg-nvidia-nemoclaw
- tools: https://api.protogrid.dev/v1/servers/io.github.Yarmoluk%2Fckg-nvidia-nemoclaw/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ckg-nvidia-nemoclaw": {
      "type": "http",
      "url": "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% ~updated-82d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 76/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: search_concepts (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ask_nemoclaw (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_prerequisites (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,325 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 16 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: 100 (weight 15)

- pass `deps.known_vulns`: no known advisory in 37 resolved packages
- pass `deps.mcp_sdk_version`: mcp 1.30.0, no known advisory
- pass `deps.resolvable`: ckg-nvidia-nemoclaw@0.10.3 resolved: 37 packages

- tools: 8, about 1,325 tokens to load them all
- tool set hash: fc9ab32ae33a21e7a421aac59f13f5ff
- tools last changed: 2026-10-07T13:41:32.864Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Yarmoluk/ckg-nvidia-nemoclaw.svg)](https://protogrid.dev/servers/io.github.Yarmoluk/ckg-nvidia-nemoclaw)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-07 `query_intersect` added
  - 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 answers it; the answer lives in the overlap. Every branch is an exact set of declared edges, so the intersection is exact. A concept appears only if a declared path reaches it from each anchor. A relation missing from the graph produces an empty result, never a guess. Args: branches: Two or more branches. Either a bare anchor ("TensorRT-LLM"), which takes everything within `depth` hops, or an anchor plus an explicit relation path using '>' ("TensorRT-LLM > REQUIRES > ENABLES"), where each relation replaces the frontier. '*' matches any relation. Mix both forms freely. depth: Hops for bare-anchor branches, 1-5 (default 2). Ignored for explicit paths. direction: 'out' follows dependencies, 'in' follows them backwards, 'both' (default). mode: 'AND' (default) intersects branches; 'OR' unions them. limit: Max concepts listed, 1-200 (default 40). The true count is always shown. Returns: Markdown with the query plan and its per-step set sizes, then the answer set with taxonomy tags. Reports which branch was empty when the intersection is empty.
- 2026-10-07 `route_query` added
  - 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 model and reasoning approach to use. Routing table: hop_depth 1 → haiku · direct (single concept lookup) hop_depth 2 → sonnet · generic_cot (moderate chain) hop_depth 3+ → opus · sparql_cot (deep chain, structured reasoning required) Args: question: Concept name or natural language question about NemoClaw / OpenShell. Returns: model_tier + reasoning_approach + why + context subgraph to inject before LLM call.
- 2026-10-07 `verify_source` added
  - 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-fetch means either the source has changed (stale edge — re-extract) or the graph was patched without re-fetching (silent edit — investigate). Audit chain: edge answer → graph commit → source_hash → source_url (fetch hint) Verification: curl -s <source_url> | sha256sum # compare output to source_hash Args: concept: Exact or partial concept label (e.g. 'CorporateCA', 'L7Proxy').
- 2026-10-07 `list_domains` added
  - List available domains in this CKG server.
- 2026-10-07 `search_concepts` added
  - Fuzzy search for NemoClaw concepts by name or keyword. Args: query: Partial name or keyword (e.g. 'policy', 'inference', 'agent').
- 2026-10-07 `get_prerequisites` added
  - 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.
- 2026-10-07 `query_ckg` added
  - 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).
- 2026-10-07 `ask_nemoclaw` added
  - 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 Blueprint, Nemotron 3 Ultra ecosystem, and platform support. Args: question: Your question about NemoClaw concepts or architecture.
- 2026-10-07 `list_domains` removed
  - List available domains in this CKG server.
- 2026-10-07 `query_intersect` removed
  - 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 answers it; the answer lives in the overlap. Every branch is an exact set of declared edges, so the intersection is exact. A concept appears only if a declared path reaches it from each anchor. A relation missing from the graph produces an empty result, never a guess. Args: branches: Two or more branches. Either a bare anchor ("TensorRT-LLM"), which takes everything within `depth` hops, or an anchor plus an explicit relation path using '>' ("TensorRT-LLM > REQUIRES > ENABLES"), where each relation replaces the frontier. '*' matches any relation. Mix both forms freely. depth: Hops for bare-anchor branches, 1-5 (default 2). Ignored for explicit paths. direction: 'out' follows dependencies, 'in' follows them backwards, 'both' (default). mode: 'AND' (default) intersects branches; 'OR' unions them. limit: Max concepts listed, 1-200 (default 40). The true count is always shown. Returns: Markdown with the query plan and its per-step set sizes, then the answer set with taxonomy tags. Reports which branch was empty when the intersection is empty.

Full history: https://api.protogrid.dev/v1/servers/io.github.Yarmoluk%2Fckg-nvidia-nemoclaw/changes

## Dependencies

- pypi ckg-nvidia-nemoclaw@0.10.3: resolved, 36 dependencies, MCP SDK mcp 1.30.0

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://ckg-nvidia-nemoclaw.onrender.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- pypi ckg-nvidia-nemoclaw@0.10.3

## Tools (8)

- `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 Blueprint, Nemotron 3 Ultra ecosystem, and platform support.

Args:
    question: Your question about NemoClaw concepts or architecture.

- `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.

- `list_domains`: List available domains in this CKG server.
- `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).

- `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 answers it; the answer lives in the overlap.

Every branch is an exact set of declared edges, so the intersection is exact. A concept
appears only if a declared path reaches it from each anchor. A relation missing from the
graph produces an empty result, never a guess.

Args:
    branches: Two or more branches. Either a bare anchor ("TensorRT-LLM"), which takes
        everything within `depth` hops, or an anchor plus an explicit relation path using
        '>' ("TensorRT-LLM > REQUIRES > ENABLES"), where each relation replaces the
        frontier. '*' matches any relation. Mix both forms freely.
    depth: Hops for bare-anchor branches, 1-5 (default 2). Ignored for explicit paths.
    direction: 'out' follows dependencies, 'in' follows them backwards, 'both' (default).
    mode: 'AND' (default) intersects branches; 'OR' unions them.
    limit: Max concepts listed, 1-200 (default 40). The true count is always shown.

Returns:
    Markdown with the query plan and its per-step set sizes, then the answer set with
    taxonomy tags. Reports which branch was empty when the intersection is empty.

- `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 model and reasoning approach to use.

Routing table:
  hop_depth 1  → haiku  · direct          (single concept lookup)
  hop_depth 2  → sonnet · generic_cot     (moderate chain)
  hop_depth 3+ → opus   · sparql_cot      (deep chain, structured reasoning required)

Args:
    question: Concept name or natural language question about NemoClaw / OpenShell.

Returns:
    model_tier + reasoning_approach + why + context subgraph to inject before LLM call.

- `search_concepts`: Fuzzy search for NemoClaw concepts by name or keyword.

Args:
    query: Partial name or keyword (e.g. 'policy', 'inference', 'agent').

- `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-fetch means either
the source has changed (stale edge — re-extract) or the graph was patched without
re-fetching (silent edit — investigate).

Audit chain:
    edge answer → graph commit → source_hash → source_url (fetch hint)

Verification:
    curl -s <source_url> | sha256sum
    # compare output to source_hash

Args:
    concept: Exact or partial concept label (e.g. 'CorporateCA', 'L7Proxy').