> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Asynchronous Streaming Agent

> Stream a Llama-powered Agno agent's response asynchronously with aprint_response().

## Code

```python async_stream.py theme={null}
import asyncio

from agno.agent import Agent
from agno.models.meta import Llama

agent = Agent(model=Llama(id="Llama-4-Maverick-17B-128E-Instruct-FP8"), markdown=True)

# Get the response in a variable
# async def main():
#     async for chunk in agent.arun("Share a 2 sentence horror story", stream=True):
#         print(chunk.content, end="", flush=True)

# Print the response in the terminal
asyncio.run(agent.aprint_response("Share a 2 sentence horror story", stream=True))
```

## Usage

<Snippet file="create-venv-step.mdx" />

**1. Set your LLAMA API key**

```bash theme={null}
export LLAMA_API_KEY=YOUR_API_KEY
```

**2. Install dependencies**

```bash theme={null}
uv pip install llama-api-client agno
```

**3. Run Agent**

```bash theme={null}
python async_stream.py
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.