A high-performance local AI orchestration layer that turns Mac Minis into scalable inference nodes for LLMs, image generation, and speech processing.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mac-mini-ai
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install mac-mini-ai using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Mac Mini AI?
The Mac Mini AI skill transforms Apple Silicon hardware into a professional-grade local inference server. By leveraging the high-bandwidth unified memory of the M4 and M4 Pro chips, this Openclaw Skills integration allows you to run everything from compact 3B models to massive 70B quantized models. It is designed for developers who want the performance of cloud GPUs without the ongoing subscription costs or privacy concerns.
This skill enables the creation of an AI fleet where multiple Mac Minis work together. A central router handles incoming requests and distributes them across your available hardware, ensuring that your local AI infrastructure is both resilient and highly performant. Whether you are building a home lab or a private dev environment, this tool simplifies the deployment of local intelligence.
Mac Mini AI Use Cases
- Deploying a cost-effective local AI home lab with no subscription fees using Openclaw Skills.
- Scaling inference capacity by clustering multiple Mac Minis into a unified compute fleet.
- Providing a private, OpenAI-compatible backend for coding assistants like Aider, Continue, or VS Code extensions.
- Running high-fidelity local image generation and speech-to-text transcription without data egress.
How Mac Mini AI Works
- Install the orchestration package on a primary Mac Mini to act as the central fleet router.
- Initialize additional Mac Minis as worker nodes which automatically discover the router on the local network.
- The router aggregates the RAM and processing power of all connected nodes to present a single API surface.
- Applications send standard OpenAI or Ollama API requests to the router address.
- The system intelligently routes the task to the specific node currently hosting the required model or with the lowest latency.
Mac Mini AI Setup
First, install the fleet manager via pip:
pip install ollama-herd
To start the primary router node, run:
herd
To add any other Mac Mini on your network to the fleet, run:
herd-node
The devices will perform automatic discovery without manual IP configuration.
Mac Mini AI Data Schema & Taxonomy
The skill manages its state and logs locally within the user's home directory. The following table describes the data organization:
| Path | Description |
|---|---|
~/.fleet-manager/latency.db |
SQLite database tracking node performance and health. |
~/.fleet-manager/logs/herd.jsonl |
Structured logs of all API requests and fleet events. |
http://localhost:11435/dashboard |
Web interface for real-time monitoring and model management. |
http://localhost:11435/v1 |
OpenAI-compatible endpoint for tool integration. |
Mac Mini AI Advanced Features
- Zero-config peer discovery using local network protocols.
- Multi-modal support including Flux for image generation and Qwen-ASR for speech processing.
- Intelligent model recommendations based on specific Mac Mini RAM configurations (16GB to 64GB).
- Built-in request queueing and load balancing across the fleet.
- Privacy-first guardrails that prevent unauthorized model downloads and ensure data never leaves the local network.
SKILL.md
Loading
Related Openclaw Skills
PRD Development
A strategic requirement engineering skill that converts raw product concepts into structured, developer-ready documentation.
Competitive Intelligence Skill
A sophisticated market research tool for AI agents that utilizes live web scraping to provide real-time competitive insights and strategic signals.
ACP Remote
A professional CLI toolset for connecting to remote Agent Client Protocol (ACP) servers to execute commands and manage agent sessions via WebSockets.
Welding Basics
A specialized AI agent skill designed to bridge the gap between digital planning and physical metal fabrication, turning you into a proficient welder in 14 days.
Mapbox Search Integration
A complete workflow for implementing Mapbox search, guiding developers from initial discovery questions to production-ready application integration.
Mapbox Search Patterns
A specialized guidance skill for AI agents to master Mapbox search tools through optimized tool selection, parameter tuning, and spatial constraints.
Featured*
