Get faster AI with Rapid-MLX, a drop-in OpenAI replacement for Apple Silicon. Ideal for founders using Claude Code, Cursor, or Aider, with 3.2k+ GitHub stars.
3,206 stars376 forksPythonQuality 8/10Updated 7/7/2026100% free ยท open source
What it does
Rapid-MLX is a drop-in OpenAI replacement that provides faster AI capabilities on Apple Silicon devices, particularly for founders using tools like Claude Code, Cursor, or Aider.
Install / run
git clone https://github.com/raullenchai/Rapid-MLX.git && cd Rapid-MLX
When to use it
โขWhen you need to accelerate AI tasks on Apple Silicon devices
โขWhen you're currently using OpenAI and want a faster, local alternative
โขWhen you're working with tools like Claude Code, Cursor, or Aider and want optimized performance
Quick start
1Run the command `python -m rapidmlx` to start the Rapid-MLX engine
2Configure the `config.json` file to set up prompt caching and reasoning separation
3Use the `--tool` flag to specify the tool parser, e.g., `--tool claude-code`
4Test the engine with a sample prompt using the `python -m rapidmlx --prompt` command
5Verify the cache hit rate using the `python -m rapidmlx --cache-stats` command
Ready-to-paste prompt
python -m rapidmlx --prompt 'Write a product description for a new smartwatch' --tool cursor
Heads up: Make sure you have Python installed on your Apple Silicon device, as Rapid-MLX is built on top of Python and requires it to run
Saves to your device
Topics
apple-silicon
claude-code
cursor
deepseek
fastapi
hacktoberfest
inference
llm
local-llm
m1
m2
m3
macos
mlx
ollama-alternative
openai-api
python
qwen
tool-calling
What's inside โ free to inspect
No purchase needed
Read the entire source before you build โ unlike paid marketplaces that hide it behind a buy button.