> ## Documentation Index
> Fetch the complete documentation index at: https://docs.julep.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Multi-Agent Multi-User Sessions

> Learn how to manage complex multi-agent systems with multiple users

## Overview

Julep supports different types of sessions based on the number of agents and users involved. This flexibility allows for complex interactions and use cases.

## Types of Sessions

<CardGroup cols={2}>
  <Card title="Single Agent" icon="user">
    <ol>
      <li>No user</li>
      <li>Single user</li>
      <li>Multiple users</li>
    </ol>
  </Card>

  <Card title="Multiple Agents" icon="users">
    <ol>
      <li>No user</li>
      <li>Single user</li>
      <li>Multiple users</li>
    </ol>
  </Card>
</CardGroup>

## Behavior in Multi-Agent/User Sessions

### User Behavior

<AccordionGroup>
  <Accordion title="No User" icon="user" defaultOpen={true}>
    <ol>
      <li>No user data is retrieved</li>
      <li>(Upcoming) Memories are not mined from the session</li>
    </ol>
  </Accordion>

  <Accordion title="One or More Users" icon="users" defaultOpen={true}>
    <ol>
      <li>Docs, metadata, memories, etc. are retrieved for all users in the session</li>
      <li>Messages can be added for each user by referencing them by name in the `ChatML` messages</li>
      <li>(Upcoming) Memories mined in the background are added to the corresponding user's scope</li>
    </ol>
  </Accordion>
</AccordionGroup>

### Agent Behavior

<AccordionGroup>
  <Accordion title="One Agent" icon="lightbulb" defaultOpen={true}>
    <ol>
      <li>Works as expected</li>
    </ol>
  </Accordion>

  <Accordion title="Multiple Agents" icon="lightbulb" defaultOpen={true}>
    <ol>
      <li>When a message is received by the session, each agent is called one after another in the order they were defined in the session</li>
      <li>You can specify which `agent` to use in a request, in which case, only that agent will be used</li>
    </ol>
  </Accordion>
</AccordionGroup>

<Note>
  This multi-agent/user capability allows for sophisticated scenarios such as:

  * Collaborative problem-solving with multiple AI agents
  * Group conversations with multiple users and agents
  * Specialized agents working together on complex tasks
</Note>

## Conclusion

By supporting these various configurations, Julep provides a flexible framework for building diverse and powerful AI applications.

## Support

If you need help with further questions in Julep:

* Join our [Discord community](https://discord.com/invite/JTSBGRZrzj)
* Check the [GitHub repository](https://github.com/julep-ai/julep)
* Contact support at [hey@julep.ai](mailto:hey@julep.ai)