AgentScope — la plataforma multi-Agent flexible de Alibaba

Quick Start — Two-Agent Debate

sequentialpipeline ejecuta los Agents en orden, pasando la salida de uno como entrada del siguiente. Para topologías más complejas usa msghub (broker de mensajes compartido) o IfElsePipeline para enrutado condicional. init() lee una lista de configs de modelos — cambiar de modelo es un cambio de config, no de código.

# pip install agentscope
import agentscope
from agentscope.agents import DialogAgent, UserAgent
from agentscope.message import Msg
from agentscope.pipelines import sequentialpipeline

# Initialize with a model config
agentscope.init(
    model_configs=[{
        "config_name": "gpt-4o-mini",
        "model_type": "openai_chat",
        "model_name": "gpt-4o-mini",
        "api_key": "sk-...",
    }],
)

bull = DialogAgent(
    name="Bull",
    sys_prompt="You argue that AI agents are overhyped. Be concise and cite one concrete data point per turn.",
    model_config_name="gpt-4o-mini",
)
bear = DialogAgent(
    name="Bear",
    sys_prompt="You argue AI agents will transform every industry within 3 years. Concise, data-backed.",
    model_config_name="gpt-4o-mini",
)

topic = Msg(name="moderator", content="Resolved: multi-agent systems will dominate enterprise SW by 2028.", role="user")
# 3 rounds of Bull → Bear using a simple pipeline
for _ in range(3):
    topic = sequentialpipeline([bull, bear], x=topic)

print("Final:", topic.content)

Características clave

Comparación

Casos de uso

Precios y licencia

Activos relacionados en TokRepo

AgentScope Studio — Agent Tracing UI

AgentScope Studio is a local visualization toolkit: Projects/Runs UI, OpenTelemetry-based tracing, and eval dashboards for AgentScope agents.

AgentScope — Distributed Multi-Agent Platform

AgentScope is a multi-agent framework supporting distributed agent communication, built-in fault tolerance, and an actor-based runtime for building complex multi-agent applications at scale.

Preguntas frecuentes