Asynchronous Streaming Agent

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

Code

async_stream.py

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

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
2. Set your LLAMA API key

   export LLAMA_API_KEY=YOUR_API_KEY
   
3. Install dependencies

   uv pip install llama-api-client agno
   
4. Run Agent

   python async_stream.py