Vibe Coding Discover

AI Frameworks

lemonade

View on GitHub

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

★ 5.8K509 forksC++Apache-2.0lemonade-sdk

Lemonade is a local AI server that runs optimized LLMs, speech, and image models on your own GPU/NPU, exposing OpenAI, Anthropic, and Ollama compatible APIs. Ships a CLI, model manager, and MCP server for connecting desktop apps and coding agents to private on-device inference.

Use Cases

Serve local LLMs to apps via OpenAI/Anthropic/Ollama APIsRun chat and coding models offline on GPU or NPULocal image generation with Stable DiffusionText-to-speech with KokoroReal-time speech transcription with WhisperEmbed local multimodal AI into desktop appsExpose local models to MCP-compatible agentsCloud offload routing to OpenAI/Fireworks/OpenRouterPoint coding assistants like Claude Code and Copilot at local modelsDownload and manage GGUF/FLM/ONNX models

Built With

Language
C++
Frameworks
llama.cpp · ONNX Runtime · ROCm · Vulkan · Metal · CUDA · Docker · CMake

Tags

local-llm · llm-inference · openai-api · onnxruntime · llamacpp · npu · rocm · vulkan · multimodal · gguf · text-to-speech · image-generation · mcp-server · amd · local-server · quantization