Use Agno with Together AI to build multimodal agents.
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 this integration.
Install libraries
uv add agno duckduckgo-search
Authentication
Set your TOGETHER_API_KEY environment variable.
export TOGETHER_API_KEY=***
Example
Below is an agent with access to web search.
from agno.agent import Agentfrom agno.models.together import Togetherfrom agno.tools.duckduckgo import DuckDuckGoToolsagent = Agent( model=Together(id="Qwen/Qwen3.5-9B"), tools=[DuckDuckGoTools()], markdown=True,)agent.print_response("What's happening in New York?", stream=True)