Claude Code Mlx Proxy

Local MLX Backend for Claude Code

This project provides a local server that acts as a backend for the Claude Code command line coding assistant. It allows you to use open-source models running on your local machine via Apple's MLX framework. Instead of sending your code to Anthropic's servers, you can use powerful models like Llama 3, GLM-4.5-Air, DeepSeek, and more, all running on your Apple Silicon Mac.

This server implements the Claude Messages API format that Claude Code communicates with, redirecting all requests to a local model of your choice.

Why Use a Local Backend with Claude Code?

- Total Privacy: Your code, prompts, and conversations never leave your local machine.
- Use Any Model: Experiment with thousands of open-source models from the MLX Community on Hugging Face.
- Work Offline: Get code completions and chat with your local model without an internet connection.
- No API Keys or Costs: Run powerful models without needing to manage API keys or pay for usage.
- Full Customization: You have complete control over model parameters and generation settings.

How to Set It Up

There are two parts: running the local server, and configuring Claude Code to use it.

Part 1: Run the Local Server

First, get the proxy server running on your machine.

1. Clone the repository:

2. Set up the environment:
    Copy the example .env file:

    You can edit the .env file to customize the model, port, and other settings (see Configuration section below).

3. Install dependencies:
    This project uses uv for fast package management.

4. Start the server:

    The server will start on http://localhost:8888 (or as configured in your .env) and begin downloading and loading the specified MLX model. This may take some time on the first run.

Part 2: Configure Claude…