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

# DaytonaSandbox 集成

> 使用 LangChain Python 集成 DaytonaSandbox 沙盒后端。

[Daytona](https://daytona.io) 提供快速启动的沙盒环境，支持多语言。请参考 [Daytona 文档](https://www.daytona.io/docs) 获取注册、身份验证和平台详情。

## 安装

```bash pip theme={null}
pip install langchain-daytona
```

```bash uv theme={null}
uv add langchain-daytona
```

## 创建沙盒后端

在 Python 中，您使用提供方 SDK 创建沙盒，并通过包裹 [deepagents backend](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/backends.md) 实现深度智能体集成。

```python theme={null}
from daytona import Daytona

from langchain_daytona import DaytonaSandbox

sandbox = Daytona().create()
backend = DaytonaSandbox(sandbox=sandbox)

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

## 使用与深度智能体

```python theme={null}
from daytona import Daytona
from langchain_anthropic import ChatAnthropic

from deepagents import create_deep_agent
from langchain_daytona import DaytonaSandbox

sandbox = Daytona().create()
backend = DaytonaSandbox(sandbox=sandbox)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-6"),
    system_prompt="You are a coding assistant with sandbox access.",
    backend=backend,
)

result = agent.invoke(
    {
        "messages": [
            {"role": "user", "content": "Create a hello world Python script and run it"}
        ]
    }
)
```

## 清理

您需通过 Daytona SDK 管理沙盒生命周期。
完成时，请停止或销毁沙盒。

参见：[Sandboxes](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/sandboxes.md)。

***

> 官方原文：[src/oss/python/integrations/sandboxes/daytona.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/sandboxes/daytona.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.