n8n

Run AI locally and on the edge

n8n now has comprehensive support for Lemonade, an open-source language model server that enables local and self-hosted AI models through an OpenAI-compatible API.

Run local LLMs with optimized performance by configuring inference engines for AMD’s NPUs and GPUs.

Use these Lemonade nodes to get started:

🍋 Lemonade Chat Model - chat-based language model with enhanced AI Agent compatibility
🍋 Lemonade Model - text completion
🍋Lemonade Embeddings - text embeddings generation

n8n.io/integrations/

3 days ago | [YT] | 800