Use Case
mlx-local-inference is a powerful AI agent skill that extends your assistant with new capabilities. Use when calling local AI on this Mac β text generation, embeddings, speech-to-text, OCR, or image understanding. LLM/VLM via oMLX gateway at localhost:8000/... This guide walks you through installing mlx-local-inference, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install mlx-local-inference: npx clawhub@latest --dir ~/.claude/skills install mlx-local-inference
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to design & creative to trigger mlx-local-inference
Review the output and refine your prompt for better results
Combine mlx-local-inference with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing mlx-local-inference
Help me get started with mlx-local-inference
What can mlx-local-inference do for my design & creative workflow?
Show me an example of using mlx-local-inference
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install mlx-local-inferenceOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install mlx-local-inferenceβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/mlx-local-inference/π‘Extract and place the folder at the path above, then restart your agent.