AutoGen

Build multi-agent conversations with Microsoft's AutoGen framework.

Language:PythonProviders:OpenAI, Anthropic

Quick start

1

Create the project

npx agentvoy create my-project --framework autogen --provider openai --model gpt-4o --yes
2

Install and run

cd my-project-agent
pip install -r requirements.txt
cp .env.example .env
# Add your API key
python run.py

What gets generated

from autogen import AssistantAgent, UserProxyAgent

llm_config = {
    "config_list": [{
        "model": "gpt-4o",
        "api_key": os.environ["OPENAI_API_KEY"],
    }],
}

def create_agent():
    assistant = AssistantAgent(
        name="agent",
        system_message="You are a helpful AI assistant...",
        llm_config=llm_config,
    )
    return assistant

Provider support

ProviderConfigGuide
OpenAIapi_key from OPENAI_API_KEYGet key
Anthropicapi_type: "anthropic"Get key

When to use AutoGen

  • You want agents that converse with each other
  • You need a UserProxy agent pattern for human-in-the-loop workflows
  • You're building agents that need code execution capabilities