SDK de agentes de Strands

Utilice el SDK de Strands Agents para lograr una integración perfecta con los marcos de los agentes, lo que permite gestionar y recuperar la memoria de forma automática en los agentes conversacionales.

En primer lugar, cree una memoria con las tres estrategias a largo plazo. Puede hacerlo con la AgentCore CLI o mediante el código SDK de los ejemplos siguientes.

Instale las dependencias

pip install bedrock-agentcore
pip install strands-agents

Agregue memoria a corto plazo

from datetime import datetime
from strands import Agent
from bedrock_agentcore.memory import MemoryClient
from bedrock_agentcore.memory.integrations.strands.config import AgentCoreMemoryConfig, RetrievalConfig
from bedrock_agentcore.memory.integrations.strands.session_manager import AgentCoreMemorySessionManager

client = MemoryClient(region_name="us-east-1")
basic_memory = client.create_memory(
    name="BasicTestMemory",
    description="Basic memory for testing short-term functionality"
)

MEM_ID = basic_memory.get('id')
ACTOR_ID = "actor_id_test_%s" % datetime.now().strftime("%Y%m%d%H%M%S")
SESSION_ID = "testing_session_id_%s" % datetime.now().strftime("%Y%m%d%H%M%S")

# Configure memory
agentcore_memory_config = AgentCoreMemoryConfig(
    memory_id=MEM_ID,
    session_id=SESSION_ID,
    actor_id=ACTOR_ID
)

# Create session manager
session_manager = AgentCoreMemorySessionManager(
    agentcore_memory_config=agentcore_memory_config,
    region_name="us-east-1"
)

# Create agent
agent = Agent(
    system_prompt="You are a helpful assistant. Use all you know about the user to provide helpful responses.",
    session_manager=session_manager,
)

agent("I like sushi with tuna")
# Agent remembers this preference

agent("I like pizza")
# Agent acknowledges both preferences

agent("What should I buy for lunch today?")
# Agent suggests options based on remembered preferences

Agregue memoria a largo plazo con estrategias

from bedrock_agentcore.memory import MemoryClient
from strands import Agent
from bedrock_agentcore.memory.integrations.strands.config import AgentCoreMemoryConfig, RetrievalConfig
from bedrock_agentcore.memory.integrations.strands.session_manager import AgentCoreMemorySessionManager
from datetime import datetime

# Create comprehensive memory with all built-in strategies
client = MemoryClient(region_name="us-east-1")
comprehensive_memory = client.create_memory_and_wait(
    name="ComprehensiveAgentMemory",
    description="Full-featured memory with all built-in strategies",
    strategies=[
        {
            "summaryMemoryStrategy": {
                "name": "SessionSummarizer",
                "namespaceTemplates": ["/summaries/{actorId}/{sessionId}/"]
            }
        },
        {
            "userPreferenceMemoryStrategy": {
                "name": "PreferenceLearner",
                "namespaceTemplates": ["/preferences/{actorId}/"]
            }
        },
        {
            "semanticMemoryStrategy": {
                "name": "FactExtractor",
                "namespaceTemplates": ["/facts/{actorId}/"]
            }
        }
    ]
)

MEM_ID = comprehensive_memory.get('id')
ACTOR_ID = "actor_id_test_%s" % datetime.now().strftime("%Y%m%d%H%M%S")
SESSION_ID = "testing_session_id_%s" % datetime.now().strftime("%Y%m%d%H%M%S")

# Configure memory
agentcore_memory_config = AgentCoreMemoryConfig(
    memory_id=MEM_ID,
    session_id=SESSION_ID,
    actor_id=ACTOR_ID
)

# Create session manager
session_manager = AgentCoreMemorySessionManager(
    agentcore_memory_config=agentcore_memory_config,
    region_name="us-east-1"
)

# Create agent
agent = Agent(
    system_prompt="You are a helpful assistant. Use all you know about the user to provide helpful responses.",
    session_manager=session_manager,
)

agent("I like sushi with tuna")
# Agent remembers this preference

agent("I like pizza")
# Agent acknowledges both preferences

agent("What should I buy for lunch today?")
# Agent suggests options based on remembered preferences

Procesamiento por lotes de mensajes

Cuando batch_size es superior a 1, los mensajes se almacenan en búfer en la memoria y se envían a AgentCore Memory en una sola llamada a la API una vez que el búfer alcanza el tamaño configurado. Esto reduce la cantidad de solicitudes de API en conversaciones de alto rendimiento.

Recomendado: gestor de contexto

from strands import Agent
from bedrock_agentcore.memory.integrations.strands.config import AgentCoreMemoryConfig
from bedrock_agentcore.memory.integrations.strands.session_manager import AgentCoreMemorySessionManager

config = AgentCoreMemoryConfig(
    memory_id=MEM_ID,
    session_id=SESSION_ID,
    actor_id=ACTOR_ID,
    batch_size=10,  # Buffer up to 10 messages before sending
)

# The `with` block guarantees all buffered messages are flushed on exit
with AgentCoreMemorySessionManager(config, region_name='us-east-1') as session_manager:
    agent = Agent(
        system_prompt="You are a helpful assistant.",
        session_manager=session_manager,
    )
    agent("Hello!")
    agent("Tell me about AWS")
# All remaining buffered messages are automatically flushed here

Alternativa: cierre explícito ()

Si no puedes usar un with bloque, llama close() manualmente:

session_manager = AgentCoreMemorySessionManager(config, region_name='us-east-1')
try:
    agent = Agent(
        system_prompt="You are a helpful assistant.",
        session_manager=session_manager,
    )
    agent("Hello!")
finally:
    session_manager.close()  # Flush any remaining buffered messages

Hay más ejemplos disponibles en GitHub: https://github.com/aws/bedrock-agentcore-sdk-python/tree/main/src/bedrock_agentcore/memory/integrations/strands