Scribd
Upload
156 views2 pages

Autogen Basics

AutoGen is a framework for creating AI agents and applications, featuring tools like Magentic-One CLI for multi-agent assistance, and Studio for prototyping without coding. It includes AgentChat for building conversational applications and Core for scalable multi-agent systems. Extensions are available for integrating with external services and community tools.

Uploaded by

FranMorón10
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
156 views2 pages

Autogen Basics

AutoGen is a framework for creating AI agents and applications, featuring tools like Magentic-One CLI for multi-agent assistance, and Studio for prototyping without coding. It includes AgentChat for building conversational applications and Core for scalable multi-agent systems. Extensions are available for integrating with external services and community tools.

Uploaded by

FranMorón10
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

AutoGen

A framework for building AI agents and applications


Magentic-One CLI PyPi magentic-one-cli

A console-based multi-agent assistant for web and file-based tasks. Built on AgentChat.
pip install -U magentic-one-cli
m1 "Find flights from Seattle to Paris and format the result in a table"

Studio PyPi autogenstudio


An app for prototyping and managing agents without writing code. Built on AgentChat.

pip install -U autogenstudio


autogenstudio ui --port 8080 --appdir ./myapp

AgentChat PyPi autogen-agentchat

A programming framework for building conversational single and multi-agent applications.


Built on Core. Requires Python 3.10+.
# pip install -U "autogen-agentchat" "autogen-ext[openai]"
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

async def main() -> None:


agent = AssistantAgent("assistant", OpenAIChatCompletionClient(model="gpt-4o"))
print(await agent.run(task="Say 'Hello World!'"))

asyncio.run(main())
Start here if you are building conversational agents. Migrating from AutoGen 0.2?.

Core PyPi autogen-core


An event-driven programming framework for building scalable multi-agent AI systems.
Example scenarios:

Deterministic and dynamic agentic workflows for business processes.

Research on multi-agent collaboration.

Distributed agents for multi-language applications.

Start here if you are building workflows or distributed agent systems.

Extensions PyPi autogen-ext


Implementations of Core and AgentChat components that interface with external services or
other libraries. You can find and use community extensions or create your own. Examples of
built-in extensions:
LangChainToolAdapter for using LangChain tools.

OpenAIAssistantAgent for using Assistant API.

DockerCommandLineCodeExecutor for running model-generated code in a Docker


container.

GrpcWorkerAgentRuntime for distributed agents.

You might also like