skills.rest
villadalmine
villadalmineCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai

Deploy and route an AI agent stack on ARM64 K3s clusters.

1|Updated Apr 3, 2026
Search Tags:#devops#ai#kubernetes#openrouter#arm64#kaniko#litellm
One-click install
npx skills add https://github.com/villadalmine/infra --skill ai-villadalmine
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai
Source: https://github.com/villadalmine/infra/tree/main/.agents/skills/ai
Command: npx skills add https://github.com/villadalmine/infra --skill ai-villadalmine

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns a homelab K3s cluster into a fully managed AI operations platform, removing the friction of wiring together chat agents, model routing, custom builds, and cluster tooling by hand.

Core Features & Use Cases

  • AI Agent Stack: Deploys Hermes Agent for self-improving assistance, HolmesGPT for SRE incident analysis, and OpenClaw for a personal AI gateway.
  • Model Routing with Fallbacks: Uses an in-cluster LiteLLM proxy to route requests across OpenRouter, local Ollama, and cloud fallback tiers without changing client code.
  • ARM64 Cluster Support: Builds amd64-only components into ARM64-compatible images with kaniko and publishes them through a local registry.
  • Operational Use Case: Run one skill to bootstrap the AI namespace, registry, secrets, and deployment paths needed for cluster copilots and user-facing chat services.

Quick Start

Ask the AI to deploy and troubleshoot the cluster AI stack for Hermes, HolmesGPT, and OpenClaw on your ARM64 K3s environment.

Frequently Asked Questions about ai

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

FAQPage Schema
How do I deploy AI agents on an ARM64 K3s cluster?▼

Deploy AI agents on an ARM64 K3s cluster by bootstrapping a dedicated AI namespace, local registry, and secrets using kaniko for native Kubernetes builds. This automates routing and deployment for cluster copilots and chat services.

Can I use LiteLLM to route models with OpenRouter fallbacks in Kubernetes?▼

Yes, LiteLLM routes model requests across OpenRouter, local Ollama, and cloud fallback tiers within Kubernetes without changing client code. This proxy ensures continuous operations even if a primary model provider fails.

How do I build ARM64-compatible images for K3s using kaniko?▼

Build ARM64-compatible images for K3s using kaniko to compile amd64-only components into ARM64 formats and publish them through a local Docker registry. This enables native deployment on ARM64 cluster nodes.

What AI operations tools can I run on a homelab K3s cluster?▼

Run Hermes for self-improving assistance, HolmesGPT for SRE incident analysis, and OpenClaw for a personal AI gateway on a homelab K3s cluster. This transforms the cluster into a fully managed AI operations platform.

Does deploying an AI agent stack on K3s require a local Docker registry?▼

Yes, deploying the AI agent stack on K3s requires a local Docker registry to store ARM64-compatible images built with kaniko. It also requires OpenRouter fallback chains and Kubernetes-native deployment configurations.

Related Skills

Explore More Software Engineering Skills→
villadalminevilladalmine
1

k3s

Manage K3s cluster operations on ARM64 nodes and control-plane services.

Community
Advanced
Azeem-2Azeem-2

aiops

Automate IT operations decisions with AIOps patterns for monitoring and incident response.

Community
Advanced
TitoPrauseeTitoPrausee

ollama-launch-setup

Configures Ollama launch integrations for third-party coding agents.

Community
Intermediate
rish2jainrish2jain

nvidia-nim

Deploy and operate NVIDIA Inference Microservices for GPU-accelerated AI inference.

Community
Advanced