> For the complete documentation index, see [llms.txt](https://supersonic-ai.gitbook.io/supersonic-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://supersonic-ai.gitbook.io/supersonic-documentation/under-the-hood/multi-agent-system.md).

# Multi-Agent System

SuperSonic's power comes from its innovative Multi-Agent System (MAS) architecture, where multiple AI agents work together harmoniously to deliver a comprehensive DeFi experience. This document explains how our MAS works and why it's a game-changer for DeFi operations. Want to see our agents in action? Check out our [User Guide](/supersonic-documentation/getting-started/user-guide.md) or explore our complete [Agents Directory](/supersonic-documentation/under-the-hood/agents-directory.md).

### Why Multi-Agent Systems? 🎯

Traditional DeFi tools often use single-purpose bots or monolithic systems. Our multi-agent approach offers several key advantages:

* **Specialization**: Each agent excels at specific tasks, leading to better performance
* **Redundancy**: Multiple agents can handle similar tasks, ensuring system reliability
* **Scalability**: New agents can be added without disrupting existing operations
* **Flexibility**: Agents can be updated or replaced individually
* **Emergent Intelligence**: Agents collaborate to solve complex problems

### Our Agent Architecture 🏗️

#### Core Components

1. **Orchestration Layer**
   * n8n as the primary coordination and orchestration system.
   * ElizaOS as the main agentic framework for protocols and tools integration.
2. **Agent Types**
   * Internal
   * Public
   * Private

#### Communication Flow

<figure><img src="/files/U8AE69rDPZBF5nQB9y3p" alt=""><figcaption></figcaption></figure>

### ElizaOS Integration 🔄

ElizaOS serves as our primary agentic framework, providing:

* Agent Runtime
* Clients Integration
* Plugins Integration
* On-Chain Features

### n8n Workflow Automation 🔧

n8n powers our automated workflows and agent orchestration, handling:

* Agent trigger conditions
* Data transformation
* API integrations
* Error handling
* Task scheduling

### Future Developments 🚀

We're continuously evolving our MAS with:

* Advanced AI models integration
* Enhanced collaboration patterns
* Improved learning capabilities
* New agent specializations
* Extended protocol support

### Getting Started with MAS Development 💻

For developers looking to extend our MAS:

1. Review our [Developer Quick Start](/supersonic-documentation/for-developers/developer-quick-start.md)
2. Explore [ElizaOS Plugin](/supersonic-documentation/for-developers/elizaos-plugin.md) documentation
3. Study [n8n Workflows](/supersonic-documentation/for-developers/n8n-workflows.md) examples
4. Check [Deployment Options](/supersonic-documentation/for-developers/deployment-options.md)

### Additional Resources 📚

* [System Overview](/supersonic-documentation/under-the-hood/system-overview.md)
* [Agents Directory](/supersonic-documentation/under-the-hood/agents-directory.md)
* [Integrations](/supersonic-documentation/under-the-hood/integrations.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://supersonic-ai.gitbook.io/supersonic-documentation/under-the-hood/multi-agent-system.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.