lemonade-sdk/lemonadeMCPClaude Skill

lemonade

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

4.3kstars

339forks

C++

aiamdgenaigpullamallmllm-inferencelocal-servermcpmcp-servermistralnpu

Quality signals

ActiveNo testsNo CIThin docsNo licensePopular

Open Repository Download ZIP

AI summary

Auto-generated overview of what this skill does and when to reach for it.

Run AI models locally on your GPU/NPU instead of the cloud with Lemonade’s open-source server or embeddable binary.

Use this when

You want to run LLMs privately without cloud costs
Your app needs multi-modal AI (text, image, speech) offline
You’re building on AMD Ryzen AI or Radeon hardware
You need an OpenAI-compatible API for local models
You’re testing models before deploying to production

Don't use when

You need real-time cloud-scale inference
Your hardware lacks a GPU/NPU for acceleration
You require strict enterprise support contracts

Capabilities

Serves optimized LLMs via OpenAI/Anthropic/Ollama APIs
Auto-optimizes models for AMD Ryzen AI, Radeon, and Strix Halo PCs
Comes as a server or embeddable binary for apps
Includes built-in chat, image, and speech generation UIs
Supports Windows, Linux, macOS, Docker, and mobile
Integrates with 15+ apps via marketplace (Claude Code, n8n, etc.)

Install

Universal installANY TOOL

$ npx skillcity@latest lemonade-sdk/lemonade

Auto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.

Requires Node.js 18+ (ships with npx).

Prefer to set it up by hand? Clone the repository:

git clone https://github.com/lemonade-sdk/lemonade.git

Loading README…

Discover the toolingbehind modern intelligence

lemonade