> ## Documentation Index
> Fetch the complete documentation index at: https://cndoc-langchain.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AgentCoreSandbox 集成

> 使用 LangChain Python 与 AgentCoreSandbox 沙箱后端集成。

[Amazon Bedrock AgentCore 代码解释器](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-tool.html) 是 [Deep Agents](https://github.com/langchain-ai/deepagents) 的沙箱后端，可在隔离的 MicroVM 环境中实现安全的代码执行。

## 安装

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install langchain-agentcore-codeinterpreter
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langchain-agentcore-codeinterpreter
  ```
</CodeGroup>

## 创建沙箱后端

有关用法、文件操作和生命周期详情，请参阅[沙箱指南](/oss/python/deepagents/sandboxes)。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from bedrock_agentcore.tools.code_interpreter_client import CodeInterpreter
from langchain_agentcore_codeinterpreter import AgentCoreSandbox

interpreter = CodeInterpreter(region="us-west-2")
interpreter.start()

backend = AgentCoreSandbox(interpreter=interpreter)
result = backend.execute("echo hello")
print(result.output)

interpreter.stop()
```

## 与 Deep Agents 一起使用

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from bedrock_agentcore.tools.code_interpreter_client import CodeInterpreter
from langchain_agentcore_codeinterpreter import AgentCoreSandbox
from langchain_anthropic import ChatAnthropic

from deepagents import create_deep_agent

interpreter = CodeInterpreter(region="us-west-2")
interpreter.start()

backend = AgentCoreSandbox(interpreter=interpreter)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-20250514"),
    system_prompt="You are a coding assistant with sandbox access.",
    backend=backend,
)

try:
    result = agent.invoke(
        {"messages": [{"role": "user", "content": "Write and run a Python script"}]}
    )
finally:
    interpreter.stop()
```

## 清理

完成后请务必停止解释器以释放资源。

另请参阅：[沙箱](/oss/python/deepagents/sandboxes)。

***

<div className="source-links">
  <Callout icon="terminal-2">
    [将这些文档](/use-these-docs)通过 MCP 连接到 Claude、VSCode 等，以获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/sandboxes/aws.mdx) 或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>