mac-mini-server
Set up OpenClaw on Mac Mini as always-on AI server — hardware recommendations, macOS config, Docker Desktop, launchd auto-start, Tailscale remote access, and cost comparison vs VPS. Use when deploying OpenClaw on Mac Mini for 24/7 personal AI.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aiwithabidi/mac-mini-server🖥️ Mac Mini Server
Complete guide to running OpenClaw on a Mac Mini as an always-on AI server. From hardware selection to monitoring.
1. Hardware Recommendations
Mac Mini M4 (2024) — $499 base
| Spec | Base | Upgraded |
|---|---|---|
| CPU | 10-core | 10-core |
| GPU | 10-core | 10-core |
| RAM | 16GB | 32GB (+$200) |
| Storage | 256GB | 512GB (+$200) |
Best for: Personal assistant, small team, cloud API-only usage. Recommendation: Upgrade to 32GB RAM ($699 total) — worth it for Docker overhead + future local models.
Mac Mini M4 Pro — $1,399 base
| Spec | Base | Upgraded |
|---|---|---|
| CPU | 12-core | 14-core |
| GPU | 16-core | 20-core |
| RAM | 24GB | 48GB (+$200) / 64GB (+$400) |
| Storage | 512GB | 1TB (+$200) |
Best for: Local model inference (Ollama), multiple clients, heavy workloads. Recommendation: 48GB RAM ($1,599) for running 7B-13B models locally alongside OpenClaw.
Which One?
| Use Case | Pick | Why |
|---|---|---|
| Cloud APIs only (Claude, GPT) | M4 32GB | Plenty of power, great value |
| Local + cloud hybrid | M4 Pro 48GB | Run Ollama + OpenClaw together |
| Multi-client server | M4 Pro 64GB | Headroom for multiple agents |
| Budget-conscious | M4 16GB | Works fine for single user |
2. macOS Initial Setup
Disable Sleep & Energy Settings
# Prevent sleep entirely
sudo pmset -a sleep 0
sudo pmset -a disksleep 0
sudo pmset -a displaysleep 0
# Restart after power failure
sudo pmset -a autorestart 1
# Disable hibernation
sudo pmset -a hibernatemode 0
# Verify settings
pmset -g
System Settings UI path: System Settings → Energy → set all to Never.
Enable Auto-Login
- System Settings → Users & Groups → Automatic Login → select your user
- System Settings → Lock Screen → disable "Require password"
⚠️ Only do this on a physically secure machine. The Mac Mini should be in a locked location.
Disable Automatic Updates Reboots
# Prevent auto-restart for updates
sudo defaults write /Library/Preferences/com.apple.SoftwareUpdate AutomaticallyInstallMacOSUpdates -bool false
Update manually on your schedule instead.
Enable Remote Access
# Enable SSH
sudo systemsetup -setremotelogin on
# Enable Screen Sharing (optional)
sudo defaults write /var/db/launchd.db/com.apple.launchd/overrides.plist com.apple.screensharing -dict Disabled -bool false
sudo launchctl load -w /System/Library/LaunchDaemons/com.apple.screensharing.plist
3. Homebrew + Docker Desktop
Install Homebrew
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
echo 'eval "$(/opt/homebrew/bin/brew shellenv)"' >> ~/.zprofile
eval "$(/opt/homebrew/bin/brew shellenv)"
Install Docker Desktop
brew install --cask docker
# Launch Docker Desktop
open -a Docker
# Wait for Docker to start, then verify
docker --version
docker compose version
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aiwithabidi-mac-mini-server": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
freshsales
Freshsales CRM integration — manage contacts, leads, deals, accounts, tasks, and sales sequences via the Freshsales API. Track deal pipelines, automate lead assignments, log activities, and generate sales reports. Built for AI agents — Python stdlib only, no dependencies. Use for sales CRM, contact management, deal tracking, pipeline reporting, and sales automation.
gemini-video-analyzer
Native video analysis using Google Gemini API. Upload and analyze video files — describe scenes, extract text/UI, answer questions about content, transcribe speech, identify objects and actions. Use when: (1) User sends a video file and wants it analyzed, (2) Video summarization or description needed, (3) Extracting text, UI elements, or information from screen recordings, (4) Answering questions about video content, (5) Comparing multiple videos, (6) Analyzing tutorials, demos, or walkthroughs.
agent-memory
Full AI agent memory stack — Mem0 unified memory engine with vector search (Qdrant) and knowledge graph (Neo4j), plus SQLite for structured data. Complete setup script and tools. Give your OpenClaw agent a real brain with semantic recall, entity relationships, and structured storage.
neon
Neon serverless Postgres — manage projects, branches, databases, roles, endpoints, and compute via the Neon API. Create database branches for development, manage connection endpoints, scale compute, and monitor usage. Built for AI agents — Python stdlib only, zero dependencies. Use for serverless Postgres, database branching, database management, development workflows, and cloud database automation.
onepassword
1Password Connect — vaults, items, secrets management for server-side applications.