skills.rest
bga23
bga23COMMUNITY
Explore all skills by this author →
GitHub

nemoclaw-user-configure-inference

Configure NemoClaw onboarding and runtime inference routing across providers.

Updated Aug 23, 2026
Search Tags:#onboarding#inference#ollama#provider#vllm#local-server#nemoclaw
One-click install
npx skills add https://github.com/bga23/NemoClaw --skill nemoclaw-user-configure-inference-bga23
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nemoclaw-user-configure-inference
Source: https://github.com/bga23/NemoClaw/tree/main/.agents/skills/nemoclaw-user-configure-inference
Command: npx skills add https://github.com/bga23/NemoClaw --skill nemoclaw-user-configure-inference-bga23

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Configures NemoClaw onboarding and runtime inference routing to unify provider switching and connect NemoClaw to a local inference server, enabling seamless provider transitions without restarting the sandbox.

Core Features & Use Cases

  • Guides onboarding through multiple providers (NVIDIA Endpoints, OpenAI-compatible, Anthropic-compatible, Google Gemini) and local servers (Ollama, vLLM, NIM) with clear expectations.
  • Enables switching the active inference provider and model at runtime without rebuilds, including non-interactive and experimental setups.
  • Documents how to set up and connect to local model servers and how the OpenShell routing interacts with local endpoints.

Quick Start

Describe how to configure NemoClaw onboarding to switch between inference providers and connect to a local model server.

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 switch inference providers in NemoClaw without recreating the sandbox?▼

You can switch inference providers in NemoClaw at runtime without rebuilds by applying the onboarding and OpenShell routing configuration. This unifies provider transitions across local servers and remote endpoints seamlessly.

Can I connect NemoClaw to a local Ollama or vLLM server for inference?▼

Yes, NemoClaw connects to local inference servers like Ollama, vLLM, and NIM. The configuration documents how to set up local endpoints and ensures the OpenShell routing interacts correctly with your local server.

Does NemoClaw onboarding support non-interactive inference provider setups?▼

NemoClaw onboarding supports both interactive and non-interactive setups for inference routing. This allows you to configure provider switching across NVIDIA Endpoints, OpenAI, Anthropic, and Gemini programmatically.

What is the best way to configure NemoClaw runtime inference routing across multiple providers?▼

The best way to configure NemoClaw runtime inference routing is through the onboarding wizard. It wires the OpenShell routing correctly across NVIDIA Endpoints, OpenAI, Anthropic, Google Gemini, and local servers.

Why does my NemoClaw OpenShell routing fail to switch to a local inference endpoint?▼

OpenShell routing fails to switch to local inference endpoints when the onboarding wizard is not wired correctly. You must ensure the NemoClaw configuration properly maps the runtime inference routing to your local server.

Do I need to restart the sandbox when changing the active inference model in NemoClaw?▼

No, you do not need to restart the sandbox when changing the active inference model in NemoClaw. The configuration enables switching the active inference provider and model at runtime without rebuilds.

Related Skills

Explore More Software Engineering Skills→
rblake2320rblake2320

nemoclaw-user-configure-inference

Configure NemoClaw to route inference to local Ollama, vLLM, or NIM servers.

Community
Advanced
sayalinvidiasayalinvidia

nemoclaw-user-configure-inference

Configure NemoClaw to route sandboxed inference to local OpenAI-compatible endpoints.

Community
Intermediate
rblake2320rblake2320

nemoclaw-user-overview

Onboard and manage sandboxed OpenClaw operations within OpenShell.

Community
Advanced
NVIDIANVIDIA
22.1k

nemoclaw-user-configure-inference

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

Official
Advanced