skills.rest
NVIDIA
NVIDIAOFFICIAL
Explore all skills by this author →
WebsiteGitHub

nemoclaw-user-configure-inference

Configure NeMoClaw inference providers and routes from the onboard wizard or at runtime without restarting the sandbox.

22.1k|3.0k|Updated Mar 15, 2026
Search Tags:#onboarding#inference#model-switching#provider-configuration#local-inference#nemoclaw
One-click install
npx skills add https://github.com/NVIDIA/NemoClaw --skill nemoclaw-user-configure-inference
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nemoclaw-user-configure-inference
Source: https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-user-configure-inference
Command: npx skills add https://github.com/NVIDIA/NemoClaw --skill nemoclaw-user-configure-inference

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

NemoClaw supports multiple inference providers and requires guidance to configure which provider to use and how routing is managed within the sandbox.

Core Features & Use Cases

  • Onboard provider selection and status display
  • Local and cloud inference options (Ollama, vLLM, NVIDIA NIM, OpenAI-compatible endpoints)
  • Experimental options and validation during onboarding
  • Runtime model switching without restarting the sandbox
  • Secure handling of credentials and OpenShell routing

Use Case: When setting up NemoClaw onboard, you can explain available providers, choose a provider, and switch models on demand.

Quick Start

Run the NemoClaw onboard wizard and choose a provider to configure inference routing.

Frequently Asked Questions about nemoclaw-user-configure-inference

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure inference providers during NemoClaw onboarding?▼

To configure NemoClaw inference providers during onboarding, run the onboard wizard to select a provider, validate available endpoints, and establish routing for local or cloud models.

Can I switch inference models at runtime without restarting the sandbox?▼

Yes, you can switch inference models at runtime without restarting the sandbox by executing specific step-by-step commands to dynamically change the active provider.

What local and cloud inference options are supported for provider configuration?▼

Supported inference options include local providers like Ollama and vLLM, alongside cloud endpoints such as NVIDIA NIM and OpenAI-compatible APIs for flexible model routing.

How do I validate inference endpoints when selecting a provider?▼

Endpoint validation occurs during the onboarding wizard sequence, checking the selected provider's connection status and available options before finalizing the inference routing configuration.

Does NemoClaw securely handle credentials for OpenShell routing and cloud inference?▼

Yes, NemoClaw implements secure handling of credentials and OpenShell routing to protect access keys when configuring cloud inference providers like NVIDIA NIM or OpenAI-compatible endpoints.

Related Skills

Explore More Software Engineering Skills→
camoneartcamoneart
5

hybrid-cloud-networking

Configure VPN, Direct Connect, and ExpressRoute for hybrid cloud networks.

Community
Advanced
Umbral-BotUmbral-Bot

provider-status

Query the Worker API for LLM provider status, quota usage, and routing configurations.

Official
Basic
RachasumanthRachasumanth

inference-deploy

Deploy trained machine learning models for inference using vLLM, TGI, Ollama, and llama.cpp.

Community
Advanced
ever-oliever-oli
3

serving-llms-vllm

Deploy and manage vLLM servers for high-throughput LLM inference.

Community
Advanced