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

# LiveKit Agent Integration

> Set up and run a LiveKit Agent server for Streaming Avatar integration

## Overview

[LiveKit Agents](https://docs.livekit.io/agents/) is a framework for building server-side AI agents that interact with users in real time. By integrating with AKOOL's Streaming Avatar, you can build AI-powered avatar experiences using LiveKit's agent infrastructure.

This guide walks you through setting up the AKOOL LiveKit Agent server locally and testing it with the LiveKit Playground.

**Repository:** [AKOOL LiveKit Agents](https://github.com/AKOOL-Official/livekit_agents)

## Prerequisites

* Python (LTS version)
* [uv](https://docs.astral.sh/uv/) package manager
* A [LiveKit Cloud](https://cloud.livekit.io/) account (for API key, secret, and server URL)
* An [OpenAI](https://platform.openai.com/) API key
* AKOOL Client ID and Client Secret (available from your [AKOOL dashboard](https://akool.com))

## Setup

<Steps>
  <Step title="Clone the repository">
    ```bash theme={null}
    git clone https://github.com/AKOOL-Official/livekit_agents.git
    cd livekit_agents
    ```
  </Step>

  <Step title="Switch to the feature branch">
    ```bash theme={null}
    git checkout feature/livekit-plugins-akool
    ```
  </Step>

  <Step title="Install dependencies">
    Run the following command in the project root directory:

    ```bash theme={null}
    uv sync
    ```
  </Step>

  <Step title="Configure environment variables">
    Navigate to the `examples` folder and create a `.env` file from the template:

    ```bash theme={null}
    cd examples
    cp env.example .env
    ```

    Fill in the following credentials in the `.env` file:

    ```
    LIVEKIT_API_KEY=""
    LIVEKIT_API_SECRET=""
    LIVEKIT_URL=""
    OPENAI_API_KEY=""
    AKOOL_CLIENT_ID=""
    AKOOL_CLIENT_SECRET=""
    ```
  </Step>

  <Step title="Start the agent server">
    ```bash theme={null}
    uv run examples/avatar_agents/akool/agent_worker.py dev
    ```
  </Step>

  <Step title="Test in the playground">
    Open the [LiveKit Agents Playground](https://agents-playground.livekit.io/) and sign in with your LiveKit account to interact with the agent.
  </Step>
</Steps>