autogen-agents

Overview

AutoGen is a framework for building multi-agent conversation systems. Agents chat with each other to solve tasks, with built-in code execution, tool use, and human-in-the-loop patterns.

Capabilities

• Create conversational agents with specific roles
• Enable code execution in sandboxed environments
• Build group chats with multiple agents
• Integrate function calling and tool use
• Support human-in-the-loop via UserProxyAgent
• Use nested conversations for complex workflows

When to Use

Trigger phrases:

• "autogen agents"

• "AutoGen multi-agent conversations — AssistantAgent, UserProxyAgent, group chat, "

• Building conversational AI systems with multiple perspectives

• Needing agents that write and execute code

• Wanting human oversight in agent conversations

• Building research, coding, or analysis teams

When NOT to Use

• Task is outside your authorization scope
• You need to implement controls (use implementing-* skills)
• Task is about analysis, not action (use analyzing-* skills)
• You don't have access to target systems
• Task requires compliance expertise (consult professionals)
• Task is about defense, not offense (use defensive skills)

Pseudo Code

# Example workflow for this skill
def execute(input_data):
    # Step 1: Validate input
    if not input_data:
        raise ValueError("Input data is required")

    # Step 2: Process core logic
    result = process(input_data)

    # Step 3: Validate output
    validate_output(result)

    return result

Basic Two-Agent Chat

from autogen import AssistantAgent, UserProxyAgent, config_list_from_json

config_list = config_list_from_json(env_or_file="OAI_CONFIG_LIST")

assistant = AssistantAgent(
    name="assistant",
    llm_config={"config_list": config_list},
    system_message="You are a helpful AI assistant.",
)

user_proxy = UserProxyAgent(
    name="user_proxy",
    human_input_mode="NEVER",  # AUTO, ALWAYS, or NEVER
    max_consecutive_auto_reply=10,
    code_execution_config={"work_dir": "coding", "use_docker": True},
)

user_proxy.initiate_chat(assistant, message="Write a Python script to analyze sales data.")