本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

# Strands 代理软件开发工具包
<a name="strands-sdk-memory"></a>

使用 [ Strands Agents ](https://strandsagents.com/latest/) SDK 与代理框架无缝集成，在对话代理中提供自动内存管理和检索。

首先，用所有三种长期策略来创造一段记忆。您可以使用 AgentCore CLI 或通过以下示例中的 SDK 代码来执行此操作。

**Example**  

1.  AgentCore CLI 内存命令必须在现有的 agentcore 项目中运行。如果你还没有，请先创建一个项目：

   ```
   agentcore create --project-name MemoryProject --no-agent
   cd MemoryProject
   ```

   然后添加内存并部署：

   ```
   agentcore add memory --name ComprehensiveAgentMemory \
     --strategies SEMANTIC,SUMMARIZATION,USER_PREFERENCE
   agentcore deploy
   ```

1. 运行打开 `agentcore` TUI，然后选择**添加**并选择**内存**：

1. 输入内存名称：  
![内存向导：输入 ComprehensiveAgentMemory 名称](https://docs.aws.amazon.com/zh_cn/bedrock-agentcore/latest/devguide/images/tui/strands-memory-add-name.png)

1. 选择所有三种策略（语义、摘要、用户首选项）：  
![记忆向导：选择所有三种记忆策略](https://docs.aws.amazon.com/zh_cn/bedrock-agentcore/latest/devguide/images/tui/strands-memory-add-strategies.png)

1. 查看配置并按 Enter 键确认：  
![记忆向导：确认 ComprehensiveAgentMemory 所有策略](https://docs.aws.amazon.com/zh_cn/bedrock-agentcore/latest/devguide/images/tui/strands-memory-add-confirm.png)

   然后运行`agentcore deploy`以配置内存 AWS。

 **安装依赖项** 

```
pip install bedrock-agentcore
pip install strands-agents
```

 **添加短期记忆 ** 

```
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
```

 **通过策略增加长期记忆 ** 

```
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
```

 **消息批处理 ** 

当大`batch_size`于 1 时，消息将在内存中缓冲，并在缓冲区达到配置的大小后通过单个 API 调用发送到 AgentCore 内存。这减少了高吞吐量对话中的 API 请求数量。

**重要**  
使用时`batch_size > 1`，**必须在会话完成`close()`后**使用`with`屏蔽或呼叫。否则，任何尚未达到批量阈值的缓冲消息都将丢失。

 *推荐：上下文管理器 * 

```
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
```

 *替代方案：显式 close () * 

如果你不能使用`with`区块，请`close()`手动调用：

```
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
```

更多示例可在以下网址获得 GitHub：[https://github.com/aws/bedrock-agentcore-sdk-python/tree/main/src/bedrock_agentcore/memory/integrations/strands](https://github.com/aws/bedrock-agentcore-sdk-python/tree/main/src/bedrock_agentcore/memory/integrations/strands)