skills.rest
rblake2320
rblake2320COMMUNITY
Explore all skills by this author →
GitHub

nemoclaw-user-configure-inference

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

Updated May 29, 2026
Search Tags:#onboarding#inference#ollama#vllm#nim#local-server#nemoclaw
One-click install
npx skills add https://github.com/rblake2320/vigil --skill nemoclaw-user-configure-inference-rblake2320
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nemoclaw-user-configure-inference
Source: https://github.com/rblake2320/vigil/tree/main/.claude/skills/nemoclaw-user-configure-inference
Command: npx skills add https://github.com/rblake2320/vigil --skill nemoclaw-user-configure-inference-rblake2320

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Configures NemoClaw to route model inference to a local server (Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible endpoint) while keeping credentials on the host and preserving sandbox isolation.

Core Features & Use Cases

  • Route NemoClaw traffic to local inference backends (Ollama, vLLM, NIM) or compatible endpoints without exposing OPENAI_API_KEY.
  • Support interactive and non-interactive onboarding, credential handling, and runtime switching between providers and models.
  • Document per-provider setup steps, workspace paths, and sub-agent configuration to enable private, offline-friendly workflows.

Quick Start

Run nemoclaw onboard with the Local Ollama provider to configure a local inference 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 route model inference to a local Ollama or vLLM server?▼

NemoClaw supports routing inference to Ollama, vLLM, NIM, TensorRT-LLM, or any OpenAI-compatible endpoint so you can run fully private, offline-friendly workflows without sending data externally.

Can I use local inference backends without exposing my OpenAI API key?▼

Yes, you can route traffic to local backends or compatible endpoints without exposing your OpenAI API key, preserving sandbox isolation while keeping provider credentials securely on the host machine.

How do I switch between local inference providers at runtime?▼

Runtime switching between providers and models is supported through interactive and non-interactive onboarding, allowing you to reconfigure endpoints and handle credentials dynamically during your workflow.

What environment variables are required to configure a local NIM inference server?▼

Configuring a local NIM inference server requires documenting specific environment variables, workspace paths, and provider credentials to validate backend support and enable secure, private deployments.

Does NemoClaw work with OpenAI-compatible endpoints for offline deployments?▼

NemoClaw works with any OpenAI-compatible endpoint, enabling offline-friendly deployments by validating multiple local backends and documenting required setup steps for private model inference.

Related Skills

Explore More Software Engineering Skills→
sayalinvidiasayalinvidia

nemoclaw-user-configure-inference

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

Community
Intermediate
VincentChong123VincentChong123

add-opencode

Integrate the OpenCode provider into NanoClaw agent infrastructure.

Community
Advanced
samelhousseinisamelhousseini

model-router

Routes chat queries to the most suitable Azure OpenAI model to minimize cost.

Community
Intermediate
dawsonblockdawsonblock

tensorrt-llm

Optimize large language model inference with NVIDIA TensorRT-LLM on multi-GPU servers.

Community
Advanced