Agno is an open-source library for creating multimodal agents. It supports interactions with text, images, audio, and video while remaining model-agnostic, allowing you to use any model in the Together AI library with our integration.

​
Install Libraries

pip install -U agno duckduckgo-search

​
Authentication

Set your TOGETHER_API_KEY environment variable. 
export TOGETHER_API_KEY=***

​
Example

Below is a simple agent with access to web search. 
from agno.agent import Agent
from agno.models.together import Together
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=Together(id="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"),
    tools=[DuckDuckGoTools()],
    markdown=True
)
agent.print_response("What's happening in New York?", stream=True)

​
Next Steps

​
Agno - Together AI Cookbook

Explore our in-depth Agno Cookbook