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

# Building a Voice Agent with LiveKit and Memobase

> [Full Code](https://github.com/memodb-io/memobase/tree/dev/assets/tutorials/livekit%2Bmemobase)

This tutorial demonstrates how to build a voice agent with long-term memory using Memobase and LiveKit. This combination is ideal for applications like AI companions, customer support bots, and more.

## Setup

1. **Get API Keys**:
   * **Memobase**: Sign up at [Memobase](https://www.memobase.io/en) or [run a local server](/references/local_config).
   * **LiveKit**: Get your `LIVEKIT_URL`, `API_KEY`, and `API_SECRET` from the [LiveKit Cloud Console](https://cloud.livekit.io/).
   * **Deepgram**: Get your `DEEPGRAM_API_KEY` from the [Deepgram Console](https://console.deepgram.com/).

2. **Environment Variables**: Set up your environment variables.

   ```bash theme={null}
   OPENAI_API_KEY="your_openai_api_key"
   DEEPGRAM_API_KEY="your_deepgram_api_key"
   LIVEKIT_URL="your_livekit_url"
   LIVEKIT_API_KEY="your_livekit_api_key"
   LIVEKIT_API_SECRET="your_livekit_api_secret"
   MEMOBASE_URL="https://api.memobase.io"
   MEMOBASE_API_KEY="your_memobase_api_key"
   ```

3. **Install Dependencies**:
   ```bash theme={null}
   pip install -r requirements.txt
   ```

## Code Breakdown

The full code is available [here](https://github.com/memodb-io/memobase/tree/dev/assets/tutorials/livekit%2Bmemobase/livekit_example.py). We will be using the [LiveKit Agents SDK v1.0](https://docs.livekit.io/agents/build/).

The core of the integration involves subclassing the `livekit.agents.Agent` class and overriding the `llm_node` method to inject memory context from Memobase.

### Agent Initialization

First, we initialize the Memobase client and define our custom agent class.

```python theme={null}
import os
from dotenv import load_dotenv
from livekit.agents import Agent, llm
from memobase import AsyncMemoBaseClient, ChatBlob
from memobase.utils import string_to_uuid

load_dotenv()
mb_client = AsyncMemoBaseClient(
    api_key=os.getenv("MEMOBASE_API_KEY"), project_url=os.getenv("MEMOBASE_URL")
)

class RAGEnrichedAgent(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions="You are a warm-hearted partner who remembers past interactions.",
        )
        self.user_name = os.getenv("MEMOBASE_USER_NAME", "test_user")
        self.chat_log_index = 1
```

### Injecting Memory

Next, we override the `llm_node` method. This method is called just before the chat history is sent to the LLM. Here, we will retrieve the user's memory from Memobase and add it to the system prompt.

```python theme={null}
async def llm_node(
    self,
    chat_ctx: llm.ChatContext,
    # ... other params
) -> AsyncIterable[llm.ChatChunk]:
    # Ensure Memobase is reachable
    assert await mb_client.ping(), "Memobase is not reachable"
    
    # Get or create the user in Memobase
    user = await mb_client.get_or_create_user(string_to_uuid(self.user_name))

    # Insert new messages into memory
    if len(chat_ctx.items) > self.chat_log_index:
        new_messages = chat_ctx.items[self.chat_log_index : len(chat_ctx.items) - 1]
        if len(new_messages):
            blob = ChatBlob(
                messages=[
                    {"role": m.role, "content": m.content[0]}
                    for m in new_messages
                    if m.role in ["user", "assistant"]
                ]
            )
            await user.insert(blob)
            await user.flush()
            self.chat_log_index = len(chat_ctx.items) - 1

    # Retrieve memory context and add to chat history
    rag_context: str = await user.context(max_token_size=500)
    chat_ctx.add_message(content=rag_context, role="system")
    
    # Call the default LLM node
    return Agent.default.llm_node(self, chat_ctx, tools, model_settings)
```

The `rag_context` string will contain the user's [profile](/features/profile/) and recent [events](/features/event/), formatted and ready to be used by the LLM.

### Running the Agent

Finally, we set up the entry point to run the agent.

```python theme={null}
async def entrypoint(ctx: JobContext):
    # ... (connect to room, set up STT, TTS, etc.)
    await session.start(
        agent=RAGEnrichedAgent(),
        # ...
    )

if __name__ == "__main__":
    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))
```

To run the code, first download the necessary assets:

```bash theme={null}
python livekit_example.py download-files
```

Then, start the agent:

```bash theme={null}
python livekit_example.py console
```

You can now have a conversation with the voice agent. It will remember information you provide across different sessions.