workflowstacks
mcp-server

Rapid-MLX: Supercharge Local AI on Apple Silicon

Rapid-MLX gives founders a lightning‑fast, OpenAI‑compatible engine for Mac M1/M2 chips—4.2× quicker than Ollama with instant tool calling. Ideal for AI‑driven product prototypes. 4.0k+ GitHub stars.

From the repo · “Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.”

4,012 stars+31★ this week436 forksPythonGuide quality 9/10 · reviewed Oct 22Updated 10/22/2026100% free · 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.

When to use it
  • •When you need to accelerate AI tasks on Apple Silicon devices
  • •When you're currently using OpenAI and want a faster, local alternative
  • •When you're working with tools like Claude Code, Cursor, or Aider and want optimized performance
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
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/rapid-mlx && curl -fsSL https://workflowstacks.com/api/skills/rapid-mlx/claude-skill -o ~/.claude/skills/rapid-mlx/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Rapid-MLX: Supercharge Local AI on Apple Silicon works
Codeflow
Free to inspect

Rapid-MLX: Supercharge Local AI on Apple Silicon is a very large Python project (~543k lines across 1121 code files, plus 1203 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Very large codebase
~543k lines · 1121 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 75%Swift 22%Shell 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    rapid_mlx/cli.py
    Where the program starts running
  4. 4
    pyproject.toml
    Dependencies and the commands it exposes
  5. 5
    rapid_mlx/__init__.py
    Inside rapid_mlx/ — the main logic begins here
What's in each folder
rapid_mlx/Core code — the actual logic607 files
apps/Sub-packages / plugins789 files
docs/Documentation338 files
examples/Examples you can copy32 files
scripts/Helper scripts179 files
reports/Folder112 files
evals/Evaluations & benchmarks103 files
proto/Data models & types33 files
READMEHas testsDocumentedCI checksExamples includedOther licenseUpdated this month
Quick Actions
Details
Creator
raullenchai
Language
Python
Category
mcp-server
Published
2/25/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/rapid-mlx.svg)](https://workflowstacks.com/skills/rapid-mlx?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 355,695
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,361
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 131,266
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 28,965
Repomix: Simplify AI Codebase Integration
Feed your codebase to AI tools easily with Repomix. For founders working with Large Language Models, backed by 26k+ GitHub stars.
mcp-server★ 1,212
Databuddy
Open-source product analytics for startups: track visitors, events, funnels, and goals without cookies, and ask Databunny, the built-in AI analyst. Uptime, feature flags, and short links in the same dashboard.
mcp-server★ 2,858
Claude Code: 425 Plugins
Get 425 plugins and 2,810 skills for automation. For startup founders using Claude Code, backed by 2.5k+ GitHub stars.