### Install and Run Frontend

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/role-playing/role_playing_frontend/README.md

Navigate to the frontend directory and install dependencies, then start the development server. Ensure the Python agent backend is running first.

```bash
cd complex-agents/role-playing/role_playing_frontend
pnpm install
pnpm dev
```

--------------------------------

### Install Dependencies and Run App

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/avatars/hedra/education_avatar/education-frontend/README.md

Install project dependencies and start the development server. Access the app at http://localhost:3000.

```bash
pnpm install
pnpm dev
```

--------------------------------

### Run the Frontend

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/exa-deep-researcher/README.md

Navigate to the frontend directory and install its dependencies using pnpm, then start the development server.

```bash
cd complex-agents/exa-deep-researcher/frontend
pnpm install
pnpm dev
```

--------------------------------

### Install and Run Frontend

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/avatars/tavus/voice-assistant-frontend/README.md

Commands to set up and start the frontend development server. Open http://localhost:3000 in your browser after running.

```bash
cd voice-assistant-frontend
npm install
npm run dev
```

--------------------------------

### Install Frontend Dependencies and Start

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/ivr-agent/README.md

Installs Node.js dependencies for the React frontend and starts the development server. This should be run in a separate terminal.

```bash
cd ivr-agent-frontend
pnpm install
pnpm dev
```

--------------------------------

### Set Up Environment Variables

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/teleprompter/teleprompter-frontend/README.md

Copies the example environment file and prompts for required LiveKit credentials. Alternatively, use the LiveKit CLI for automatic setup.

```console
lk app env --write
```

--------------------------------

### Run the Example

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/warm_handoff/README.md

Execute the Python script from the command line to start the agent and handle warm handoffs.

```console
python warm_handoff.py console

```

--------------------------------

### Install Dependencies and Configure Environment

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/nova-sonic/nova-sonic-form-agent/README.md

Installs project dependencies using pnpm and copies the example environment file. Configure your LiveKit credentials in the .env.local file.

```bash
git clone
cd nova-sonic-form-agent
pnpm install
cp .env.example .env.local
```

--------------------------------

### Start the Frontend Application

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/vision/README.md

Navigates to the frontend directory and starts the Next.js development server. Ensure Node.js and pnpm are installed.

```bash
cd agent-vision-frontend
pnpm install
pnpm dev
```

--------------------------------

### Start the Teleprompter Frontend

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/teleprompter/README.md

Navigate to the frontend directory and install its dependencies, then start the Next.js development server. This makes the teleprompter interface accessible in your browser.

```bash
cd teleprompter-frontend
npm install
npm run dev
```

--------------------------------

### Launch Frontend

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/call-moderation/README.md

Commands to install dependencies and start the frontend development server. Access the UI at http://localhost:3000.

```bash
cd ../frontend
pnpm install
cp .env.example .env.local
pnpm dev
```

--------------------------------

### Full Audio Player Agent Example

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/playing_audio/README.md

This comprehensive example sets up an agent that can play a local audio file when requested. It includes agent definition, function tool for audio playback, and server setup.

```python
import logging
from pathlib import Path
import wave
from dotenv import load_dotenv
from livekit.agents import JobContext, JobProcess, AgentServer, cli, Agent, AgentSession, inference, RunContext, function_tool
from livekit.plugins import silero
from livekit import rtc

load_dotenv()

logger = logging.getLogger("playing-audio")
logger.setLevel(logging.INFO)

class AudioPlayerAgent(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions='''
                You are a helpful assistant communicating through voice. Don't use any unpronouncable characters.
                If asked to play audio, use the `play_audio_file` function.
            '''
        )

    @function_tool
    async def play_audio_file(self, context: RunContext):
        """Play a local audio file"""
        audio_path = Path(__file__).parent / "audio.wav"

        with wave.open(str(audio_path), 'rb') as wav_file:
            num_channels = wav_file.getnchannels()
            sample_rate = wav_file.getframerate()
            frames = wav_file.readframes(wav_file.getnframes())

        audio_frame = rtc.AudioFrame(
            data=frames,
            sample_rate=sample_rate,
            num_channels=num_channels,
            samples_per_channel=wav_file.getnframes()
        )

        async def audio_generator():
            yield audio_frame

        await self.session.say("Playing audio file", audio=audio_generator())

        return None, "I've played the audio file for you."

    async def on_enter(self):
        self.session.generate_reply()

server = AgentServer()

def prewarm(proc: JobProcess):
    proc.userdata["vad"] = silero.VAD.load()

server.setup_fnc = prewarm

@server.rtc_session()
async def entrypoint(ctx: JobContext):
    ctx.log_context_fields = {"room": ctx.room.name}

    session = AgentSession(
        stt=inference.STT(model="deepgram/nova-3-general"),
        llm=inference.LLM(model="openai/gpt-5-mini"),
        tts=inference.TTS(model="cartesia/sonic-3", voice="9626c31c-bec5-4cca-baa8-f8ba9e84c8bc"),
        vad=ctx.proc.userdata["vad"],
        preemptive_generation=True,
    )

    await session.start(agent=AudioPlayerAgent(), room=ctx.room)
    await ctx.connect()

if __name__ == "__main__":
    cli.run_app(server)

```

--------------------------------

### Launch Dashboard

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/call-queue/README.md

Navigate to the frontend directory, install dependencies, configure LiveKit credentials, and start the development server. Access the dashboard via the provided URL.

```bash
cd ../frontend
pnpm install
cp .env.example .env.local  # reuse the same LIVEKIT_* values
pnpm dev
```

--------------------------------

### Full Agent Example with Function Calling

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/update_tools/README.md

This example demonstrates a complete Python agent setup. It includes defining a custom tool (`print_to_console`), prewarming resources, and dynamically updating the agent's tools with a new function (`random_number`) during an RTC session. Use this as a starting point for building your own LiveKit agents.

```python
import logging
import random
from dotenv import load_dotenv
from livekit.agents import JobContext, JobProcess, AgentServer, cli, Agent, AgentSession, inference, RunContext, function_tool
from livekit.plugins import silero

logger = logging.getLogger("function-calling")
logger.setLevel(logging.INFO)

load_dotenv()

class AddFunctionAgent(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions="""
                You are a helpful assistant communicating through voice. Don't use any unpronouncable characters.
                Note: If asked to print to the console, use the `print_to_console` function.
            """
        )

    @function_tool
    async def print_to_console(self, context: RunContext):
        print("Console Print Success!")
        return None, "I've printed to the console."

    async def on_enter(self):
        self.session.generate_reply()

server = AgentServer()

def prewarm(proc: JobProcess):
    proc.userdata["vad"] = silero.VAD.load()

server.setup_fnc = prewarm

@server.rtc_session()
async def entrypoint(ctx: JobContext):
    ctx.log_context_fields = {"room": ctx.room.name}

    session = AgentSession(
        stt=inference.STT(model="deepgram/nova-3-general"),
        llm=inference.LLM(model="openai/gpt-4.1-mini"),
        tts=inference.TTS(model="cartesia/sonic-3", voice="9626c31c-bec5-4cca-baa8-f8ba9e84c8bc"),
        vad=ctx.proc.userdata["vad"],
        preemptive_generation=True,
    )
    agent = AddFunctionAgent()

    async def _random_number() -> int:
        num = random.randint(0, 100)
        logger.info(f"random_number called: {num}")
        return num

    await agent.update_tools(
        agent.tools
        + [function_tool(_random_number, name="random_number", description="Get a random number")]
    )

    await session.start(agent=agent, room=ctx.room)
    await ctx.connect()

if __name__ == "__main__":
    cli.run_app(server)

```

--------------------------------

### Install Frontend Dependencies and Start Dev Server

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/shopify-voice-shopper/README.md

Installs Node.js dependencies and starts the Next.js development server for the frontend and Chrome extension.

```bash
cd shopify-voice-frontend
pnpm install
pnpm dev
```

--------------------------------

### Run the Example

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/replacing_llm_output/README.md

Command to execute the agent server and run the example locally.

```bash
python replacing_llm_output.py console
```

--------------------------------

### Start Development Server

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/call-queue/frontend/README.md

Starts the Next.js development server. This command should be run after installing dependencies and configuring environment variables.

```bash
pnpm dev
```

--------------------------------

### Run the Example

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/langchain_langgraph/README.md

Execute the agent server from the console.

```console
python langchain_langraph.py console
```

--------------------------------

### Run the Frontend

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/role-playing/README.md

Navigate to the frontend directory and start the development server.

```bash
cd role_playing_frontend
pnpm install && pnpm dev
```

--------------------------------

### Full Example Code

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/large_context/README.md

Provides the complete Python code for the large context LLM agent example, including all imports, setup, configuration, and execution logic.

```python
import logging
from pathlib import Path
from dotenv import load_dotenv
from livekit.agents import JobContext, JobProcess, cli, Agent, AgentSession, AgentServer, inference
from livekit.plugins import openai, google, deepgram, silero

load_dotenv()

logger = logging.getLogger("google_llm")
logger.setLevel(logging.INFO)


```

--------------------------------

### Clone Repository and Navigate

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/avatars/lemonslice/README.md

Clone the repository and navigate into the project directory to begin installation.

```bash
git clone <repository-url>
cd lemonslice
```

--------------------------------

### Setup Environment and Logging

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/keyword-detection/README.md

Loads environment variables and configures logging for the agent. Ensure you have a `.env` file with LiveKit credentials.

```python
import logging
from dotenv import load_dotenv
from livekit.agents import JobContext, JobProcess, cli, Agent, AgentSession, AgentServer, inference
from livekit.plugins import silero

load_dotenv()

logger = logging.getLogger("keyword-detection")
logger.setLevel(logging.INFO)

server = AgentServer()
```

--------------------------------

### Backend Configuration Example

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/avatars/lemonslice/README.md

Example environment variables for LiveKit and LemonSlice configuration.

```bash
# LiveKit Configuration
LIVEKIT_API_KEY=your_livekit_api_key
LIVEKIT_API_SECRET=your_livekit_api_secret
LIVEKIT_URL=wss://your-project.livekit.cloud

# LemonSlice Configuration
LEMONSLICE_API_KEY=your_lemonslice_api_key
```

--------------------------------

### Start the Frontend Development Server

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/avatars/lemonslice/README.md

Navigate to the frontend directory and start the development server.

```bash
cd frontend
pnpm dev
```

--------------------------------

### Clone Repository and Navigate to Demo

Source: https://github.com/livekit-examples/python-agents-examples/blob/main/complex-agents/avatars/anam/README.md

Clone the repository and navigate to the anam demo directory to begin setup.

```bash
git clone <repository-url>
cd complex-agents/avatars/anam
```