workflowstacks
mcp-server

vllm-mlx

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
1,637 stars+12★ this week233 forksPythonUpdated 10/20/2026100% free · open source

About this skill

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
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/vllm-mlx && curl -fsSL https://workflowstacks.com/api/skills/vllm-mlx/claude-skill -o ~/.claude/skills/vllm-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 vllm-mlx works
Codeflow
Free to inspect

Vllm-mlx is a very large Python project (~72k lines across 159 code files, plus 159 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, Apache-2.0 license, has a test suite.

Size
Very large codebase
~72k lines · 159 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 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    vllm_mlx/cli.py
    Where the program starts running
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    vllm_mlx/__init__.py
    Inside vllm_mlx/ — the main logic begins here
  5. 5
    examples/assistant_bank_en.wav
    A worked example — copy this to get going
What's in each folder
vllm_mlx/Core code — the actual logic129 files
docs/Documentation93 files
examples/Examples you can copy34 files
scripts/Helper scripts7 files
benchmarks/Evaluations & benchmarks2 files
tests/Tests — proof it works159 files
.github/CI / automation (GitHub Actions)10 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
waybarrios
Language
Python
Category
mcp-server
Published
12/6/2025

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/vllm-mlx.svg)](https://workflowstacks.com/skills/vllm-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.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 376,837
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 288,000
ECC supercharges AI‑agent performance for founders building Claude, Codex, and Cursor
Founders gain optimized skills, memory, security, and research‑first development for Claude Code, Codex, Opencode, Cursor, backed by 280k+ GitHub stars.
mcp-server★ 156,636
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★ 347
iphone-use
Open-source real iPhone control for AI agents: screen text, tap/type/swipe, custom XCTest runner, CLI + HTTP API + MCP, browser takeover and replayable flows. Rust, self-hosted on macOS.
mcp-server★ 401
vigil
Vigil: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.
mcp-server★ 80,819
OmniRoute: Unified AI Gateway Cutting Token Costs for Founders
OmniRoute lets startup founders access 290+ AI providers and 500+ models via a single endpoint, auto‑fallback and token‑saving compression. Ideal for teams building with Claude, GPT, Gemini, Copilot and more.