Ollama LLM Router Based on User Prompt

💡This agent chooses the Ollama LLM for the next AI Agent Dynamically based on the users prompt

AI Agent using Dynamic Local Ollama LLM

💡This agent uses the Ollama LLM based on previous Router agent choice and proceeds to answer the users prompt.

Who is this for?

This workflow template is designed for AI enthusiasts, developers, and privacy-conscious users who want to leverage the power of local large language models (LLMs) without sending data to external services. It's particularly valuable for those running Ollama locally who want intelligent routing between different specialized models.

What problem is this workflow solving?

When working with multiple local LLMs, each with different strengths and capabilities, it can be challenging to manually select the right model for each specific task. This workflow automatically analyzes user prompts and routes them to the most appropriate specialized Ollama model, ensuring optimal performance without requiring technical knowledge from the end user.

What this workflow does

This intelligent router:

• Analyzes incoming user prompts to determine the nature of the request
• Automatically selects the optimal Ollama model from your local collection based on task requirements
• Routes requests between specialized models for different tasks:
  • Text-only models (qwq, llama3.2, phi4) for various reasoning and conversation tasks
  • Code-specific models (qwen2.5-coder) for programming assistance
  • Vision-capable models (granite3.2-vision, llama3.2-vision) for image analysis
• Maintains conversation memory for consistent interactions
• Processes everything locally for complete privacy and data security

Setup

1. Ensure you have Ollama installed and running locally
2. Pull the required models mentioned in the workflow using Ollama CLI (e.g., ollama pull phi4)
3. Configure the Ollama API credentials in n8n (default: http://127.0.0.1:11434)
4. Activate the workflow and start interacting through the chat interface

How to customize this workflow to your needs

• Add or remove models from the router's decision framework based on your specific Ollama collection
• Adjust the system prompts in the LLM Router to prioritize different model selection criteria
• Modify the decision tree logic to better suit your specific use cases
• Add additional preprocessing steps for specialized inputs

This workflow demonstrates how n8n can be used to create sophisticated AI orchestration systems that respect user privacy by keeping everything local while still providing intelligent model selection capabilities.

🔐🦙🤖 Private & Local Ollama Self-Hosted LLM Router

Purpose and structure

This folder contains the 🔐🦙🤖 Private & Local Ollama Self-Hosted LLM Router workflow. Its executable nodes use agent, chatTrigger, lmChatOllama, memoryBufferWindow. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

When chat message received

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Stickynote/1557_Stickynote_Automation_Triggered.json MIT; preserve source notices.