n8n AI Agents Automation
8 min read AI Automation

n8n's New Chat Hub: The Ultimate AI Model Switchboard for Your Business

Tired of juggling multiple AI chat interfaces? n8n's Chat Hub finally lets you converse with Claude, GPT, and Gemini in one place while maintaining full context. Even better - trigger your custom n8n workflows directly from chat and get AI-powered analysis of your automation data.

What is n8n's Chat Hub?

Businesses using multiple AI models face a frustrating reality - each conversation is siloed in separate interfaces, forcing constant tab switching and context rebuilding. n8n's Chat Hub solves this by providing a unified interface that connects to all major AI models while maintaining conversation context across switches.

The Chat Hub appears as a chat bubble icon in the bottom left corner of your n8n instance (visible in version 1.2+). Its familiar interface resembles ChatGPT or Claude's chat, with conversation history on the left and the active chat in the center. But the real power comes from what happens behind the scenes.

Key differentiator: Unlike other chat interfaces, n8n's Chat Hub maintains your full conversation history when switching between models. Start with Claude, move to GPT-4, then try Gemini - all while keeping the same thread intact for each model to reference.

Seamless AI Model Switching

The ability to switch AI models mid-conversation changes how businesses can leverage different models' strengths. Need Claude's careful analysis followed by GPT's creative flair? The Chat Hub makes this fluid transition possible.

At the top of the chat interface, you'll find a model selector dropdown. This shows all connected AI services - including direct API connections to Anthropic's Claude, OpenAI's models, and Open Router (which provides access to Gemini and others). Simply select a different model and continue your conversation.

For example, you could:

  1. Ask Claude Haiku to analyze a business problem (1:15 in the video)
  2. Switch to GPT-4 Mini for creative solutions
  3. Move to Gemini Pro via Open Router for web-enhanced answers

All while maintaining one continuous conversation thread that each model can reference for context.

Built-in Web Search Tools

Static AI knowledge has limitations - sometimes you need live data. Chat Hub integrates with GINA AI to provide web search and URL reading capabilities directly within conversations.

The tools panel at the bottom of the chat interface shows available functions. With GINA enabled (using a free API key that provides 1 million initial tokens), you can:

  • Search the web for current information (e.g., "What is the Chicago Bears' current record?")
  • Summarize content from specific URLs
  • Verify facts against live sources

When tools are used, the chat clearly indicates when web searches or URL reads occur, making the AI's research process transparent (3:45 in the video).

Workflow Integration Magic

Chat Hub's most powerful feature is its ability to connect with your custom n8n workflows. Any workflow using the Chat Trigger node can become an "agent" accessible through the chat interface.

To make a workflow available in Chat Hub (7:30 in the video):

  1. Add a Chat Trigger node to your workflow
  2. Enable "Available in n8n Chat" in the trigger settings
  3. Give your agent a name and description
  4. Publish the workflow

Once published, your workflow appears in the "Custom Agents" section of Chat Hub. Users can then trigger it by sending messages - with the workflow's output returning through the chat interface.

Pro Tip: The demo shows a "Mean Agent" workflow that responds sarcastically (8:50). This illustrates how you can create specialized agents with distinct personalities or functions while keeping them accessible through the same unified interface.

AI-Powered Data Analysis

One transformative use case demonstrated is creating AI agents that analyze your n8n execution data (5:15 in the video). These agents can:

  • Query how many times specific workflows ran in a given period
  • Calculate total token usage across executions
  • Provide detailed breakdowns of workflow activity

The example shows an agent answering "How many times did the customer support workflow run in October?" followed by "How many total tokens did we spend with our code reviewer agent?" - with the AI correctly summing the token counts from multiple executions (10,260 tokens in the demo).

This turns your execution logs into conversational knowledge, making operational data accessible to non-technical team members through natural language queries.

Creating Custom Agents

The Chat Hub interface includes a "New Agent" button for creating custom GPT-like assistants without needing to build full workflows. These agents can:

  • Be given custom system prompts (defining their personality and capabilities)
  • Use any connected AI model as their base
  • Access the same tools as the main chat (like GINA web search)

While simpler than workflow-based agents, these are quicker to create and useful for single-purpose assistants. The interface even allows editing the AI's responses after they're generated - useful for refining outputs before sharing.

Voice Output Features

While primarily a text interface, Chat Hub includes basic text-to-speech capabilities. Each AI response has a "Read Aloud" button that will speak the text using built-in browser speech synthesis.

As shown at 4:20 in the video, the voice output is functional but lacks the polish of premium services like ElevenLabs. It serves best for quick audio verification of responses rather than customer-facing voice applications.

Other response controls include:

  • Copy button for quick sharing
  • Edit ability to modify AI responses
  • Regenerate option to get a new response

Watch the Full Tutorial

See the Chat Hub in action - from model switching (1:15) to workflow integration (7:30) to data analysis agents (5:15). The video demonstrates all the features discussed plus additional tips for getting the most from this powerful new n8n capability.

Video tutorial showing n8n Chat Hub features

Key Takeaways

n8n's Chat Hub transforms how businesses interact with AI by breaking down model silos and connecting conversations to automation workflows. Instead of juggling multiple chat interfaces, teams now have one unified control center for all their AI interactions.

In summary: Chat Hub lets you leverage each AI model's strengths while maintaining context, adds web search capabilities to conversations, and most importantly - connects directly to your custom n8n workflows, turning them into conversational agents accessible through chat.

Frequently Asked Questions

Common questions about n8n's Chat Hub

n8n's Chat Hub is a unified interface that lets you converse with multiple AI models (Claude, GPT, Gemini) in one place while maintaining conversation context when switching between them. It also allows triggering custom n8n workflows directly from chat.

Unlike separate chat interfaces for each AI service, Chat Hub preserves your conversation history across model switches and workflow triggers. This creates a seamless experience where you can leverage each model's strengths without losing context.

  • Single interface for all AI conversations
  • Maintains context when switching models
  • Triggers n8n workflows from chat

The Chat Hub appears as a chat bubble icon in the bottom left corner of your n8n instance. If you don't see it, you may need to update your n8n installation to the latest version that includes this feature.

After updating, the chat icon should appear persistently in the interface. Clicking it opens the Chat Hub panel where you can start new conversations or access previous ones. The interface is designed to be familiar to users of other AI chat services.

  • Look for the chat bubble icon in bottom left
  • Requires n8n version 1.2 or later
  • Update your instance if icon is missing

Yes, the Chat Hub maintains conversation context when switching between different AI models. You can start talking to Claude, switch to GPT, then move to Gemini - all while keeping the same conversation thread intact for each model to reference.

This context persistence is what sets n8n's solution apart. At the top of the chat, simply select a different model from the dropdown menu. The new model will have access to all previous messages in the conversation, allowing for truly continuous dialogues across AI services.

  • Switch models without losing context
  • Dropdown selector at top of chat
  • Each model sees full conversation history

Currently the main tool is GINA AI which provides web search and URL content reading capabilities. The interface also shows which tools were used during a conversation, making it transparent how answers were generated.

GINA requires an API key (with 1 million free tokens to start) and can be configured in n8n's credentials section. When enabled, it allows the AI to perform live web searches or read specific URLs to incorporate current information into its responses.

  • GINA AI for web search and URL reading
  • Free initial 1 million tokens
  • Clear indicators when tools are used

To make a workflow available in Chat Hub: 1) Use the Chat Trigger node in your workflow 2) Enable 'Available in n8n Chat' in the trigger settings 3) Publish your workflow. Once published, it will appear as a custom agent in the Chat Hub interface.

The workflow must be published (not just saved) to appear in Chat Hub. In the Chat Trigger settings, you can name your agent and provide a description that will help users understand its purpose when browsing available agents.

  • Requires Chat Trigger node in workflow
  • Must enable availability in trigger settings
  • Workflow must be published, not just saved

Yes, you can create AI agents that analyze your n8n execution logs. The demo showed an agent that could query how many times specific workflows ran in a given month and calculate total token usage across executions - with the ability to provide detailed breakdowns.

These data analysis agents connect to your execution logs (stored in n8n's database or external data stores) and can answer natural language questions about your automation activity. This makes operational metrics accessible to non-technical team members through simple chat queries.

  • Agents can query execution frequency
  • Calculate token usage across workflows
  • Provide detailed breakdowns on request

Chat Hub includes a basic text-to-speech function that can read AI responses aloud, though the voice quality is not as advanced as dedicated services like ElevenLabs. Each response has a 'Read Aloud' button next to it.

The voice output uses your browser's built-in speech synthesis capabilities. While functional for quick verification of responses, businesses needing high-quality voice output would want to connect the chat to a dedicated TTS service through a custom workflow.

  • Basic browser-based text-to-speech
  • 'Read Aloud' button on each response
  • Not production-grade voice quality

GrowwStacks can build custom n8n workflows optimized for Chat Hub integration, create specialized AI agents for your business data, and implement the complete system with your preferred AI models. We offer a free consultation to discuss specific use cases where Chat Hub could streamline your operations through AI automation.

Our team specializes in connecting n8n's capabilities to real business needs. Whether you need workflow analysis agents, model-switching strategies, or custom GPT-like assistants, we can design and implement a Chat Hub solution tailored to your requirements.

  • Custom workflow integration with Chat Hub
  • Specialized AI agent development
  • Free 30-minute consultation to explore use cases

Ready to Transform Your AI Conversations?

Juggling multiple AI interfaces wastes time and fractures context. Let GrowwStacks implement n8n's Chat Hub to unify your AI interactions and connect them directly to your business workflows.