Information
Agno home page ⌘K agno-agi/agno agno-agi/agno Search... Navigation Getting Started AI Engineering is Software Engineering from agno.agent import Agent from . import from agno.models.openai import OpenAIChat from . . import from agno.tools.duckduckgo import DuckDuckGoTools from . . import agent = Agent( = ( model=OpenAIChat(id="gpt-4o"), = ( id = "gpt-4o" ) , tools=[DuckDuckGoTools()], = [ ( ) ] , markdown=True = True ) ) agent.print_response("What's happening in New York?", stream=True) . ( "What's happening in New York?" , = True ) Key features Get Started Build with Agno Your first Agent x github discord youtube website On this page Agno is a lightweight library for building Multimodal Agents. When building AI products, 80% of your solution will be standard python code, and the remaining 20% will use Agents for automation. Agno is designed for such use cases. Write your AI logic using familiar programming constructs (if, else, while, for) and avoid complex abstractions like graphs and chains. Here’s a simple Agent that can search the web: Agno is designed to be simple, fast and model agnostic. Here are some key features: If you’re new to Agno, start here to build your first Agent. Learn how to build Agents with Agno Chat with your Agents using a beautiful Agent UI Monitor your Agents on agno.com After that, checkout the Examples Gallery to discover real-world applications built with Agno. Agno is a battle-tested framework with best-in-class performance, checkout the following guides to dive-in: Learn core Agent concepts Use any model, any provider, no lock-in Use 100s of tools to extend your Agents Add domain-specific knowledge to your Agents Add semantic search and retrieval to your Agents Persist agent states and conversations in a database Remember user details and session summaries Generate embeddings for your knowledge base Build complex workflows with Agents