version: "1.0.1" name: autogen description: >- Build conversational multi-agent systems with Microsoft AutoGen. AssistantAgent, UserProxyAgent, GroupChat, code execution, nested chats, cancellation tokens, tool integration, and MCP support. Use when building conversation-driven multi-agent systems or comparing agent frameworks. Do not use this skill for unrelated requests; route to the nearest named specialist. license: MIT metadata: author: Magnus Hedemark version: 1.2.0 source: https://microsoft.github.io/autogen

AutoGen Expert Skill

This skill targets the AutoGen AgentChat 0.7.5 API on Python 3.10+. AutoGen (by Microsoft Research) is a framework for conversational multi-agent AI. Unlike LangGraph's explicit graph topology or CrewAI's role-based crews, AutoGen uses agent-to-agent conversations as the orchestration primitive. Agents communicate through structured chat, with built-in patterns for group chat routing, human input, and code execution.

Core Paradigm

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
model_client = OpenAIChatCompletionClient(model="gpt-4o-mini")
assistant = AssistantAgent(
    name="assistant",
    system_message="You are a helpful assistant.",
    model_client=model_client,
)

Role split in AgentChat 0.7.5: UserProxyAgent represents a human and obtains replies through input_func. CodeExecutorAgent executes code blocks using a CodeExecutor. They are separate agents; neither accepts the legacy human_input_mode option.

Core Principles

1. Conversations are the orchestration primitive. Agents send messages, receive replies, and the conversation structure determines the workflow.
2. Keep human input and code execution separate. Use UserProxyAgent for a human participant; use CodeExecutorAgent with a CodeExecutor for code.
3. GroupChat routes between agents. RoundRobinGroupChat cycles fixed-order. SelectorGroupChat uses an LLM to pick the next speaker.
4. Nested chats delegate work. An agent can spawn a sub-conversation between specialist agents and return the result.
5. Docker is the safe code execution mode. Local code execution (LocalCommandLineCodeExecutor) runs LLM-generated code on your machine — use Docker in production.
6. Cancellation tokens stop runaway agents. Always pass CancellationToken for long-running tasks.

Where to Start

Quick Reference

Framework Routing Guide

Reference Files

Install the exact package versions used by the templates with python -m pip install -r requirements.txt from this skill directory. The code-execution example uses Docker and requires a working Docker daemon.

Templates

Troubleshooting

When NOT to Use AutoGen

• Simple single-agent task — overkill, use direct API call
• Need fine-grained graph control — use LangGraph
• Need role-based teams with fixed processes — use CrewAI
• Need chain composition — use LangChain LCEL