AutoGen — le framework multi-Agent conversationnel de Microsoft

Quick Start — AutoGen v0.4 AssistantAgent + RoundRobinGroupChat

La v0.4 est async-first — notez le asyncio.run(). RoundRobinGroupChat fait tourner les intervenants ; SelectorGroupChat utilise un LLM pour choisir le prochain intervenant. Les conditions de terminaison sont composables (TextMention, MaxMessage, FunctionCall, etc.). La v0.2 (encore très utilisée) a une API différente — alignez soigneusement votre version installée avec la documentation.

# pip install -U "autogen-agentchat>=0.4" "autogen-ext[openai]"
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_agentchat.conditions import TextMentionTermination
from autogen_ext.models.openai import OpenAIChatCompletionClient

async def main():
    llm = OpenAIChatCompletionClient(model="gpt-4o-mini")

    planner = AssistantAgent(
        name="planner",
        model_client=llm,
        system_message="Break the user's goal into 2-3 concrete steps. Hand off to writer.",
    )
    writer = AssistantAgent(
        name="writer",
        model_client=llm,
        system_message="Execute the plan in clear prose. Say 'APPROVE' when done.",
    )
    critic = AssistantAgent(
        name="critic",
        model_client=llm,
        system_message="Find one concrete improvement or respond 'APPROVE' if good enough.",
    )

    team = RoundRobinGroupChat(
        participants=[planner, writer, critic],
        termination_condition=TextMentionTermination("APPROVE"),
        max_turns=8,
    )
    result = await team.run(task="Write a 150-word intro to multi-agent frameworks.")
    for msg in result.messages:
        print(f"[{msg.source}] {msg.content[:120]}")

asyncio.run(main())

Fonctionnalités clés

Comparaison

Cas d'usage

Tarification et licence

Assets associés sur TokRepo

AutoGen — Microsoft Multi-Agent Conversation Framework

Framework by Microsoft Research for building multi-agent conversational AI systems. Agents chat with each other to solve tasks collaboratively. Supports human-in-the-loop and code execution. 40,000+ stars.

AutoGen — Multi-Agent Conversation Framework

Microsoft framework for building multi-agent conversational AI systems. Agents chat with each other to solve tasks. Supports tool use, code execution, and human feedback. 56K+ stars.

AG2 — Open-Source AgentOS for Multi-Agent Systems

AG2 (formerly AutoGen) is an open-source framework for building cooperating AI agents with tool use, human-in-the-loop workflows, and patterns.

AgentOps — Observability for AI Agents

Python SDK for AI agent monitoring. LLM cost tracking, session replay, benchmarking, and error analysis. Integrates with CrewAI, LangChain, AutoGen, and more. 5.4K+ stars.

Questions fréquentes