AI Model Router & Local Chatbot for Privacy-Focused Tasks

This n8n workflow enables dynamic routing of user prompts to the most suitable local large language model (LLM) in Ollama, aimed at AI enthusiasts, developers, and privacy-conscious users. It listens for incoming chat messages via a webhook, analyzes the user input, and intelligently selects the optimal Ollama LLM based on the task’s requirements using a sophisticated LLM router. The workflow supports multiple specialized models, including text reasoning, coding, and visual analysis, maintaining context with conversation memory buffers to ensure consistent interactions. Designed to keep all data processing local, this setup ensures user privacy and security while providing versatile AI capabilities. Perfect for automating intelligent decision-making in local AI deployments, improving task-specific performance, and managing complex multi-model interactions seamlessly.