AgentCoreSandbox 集成

使用 LangChain Python 与 AgentCoreSandbox 沙箱后端进行集成。

Amazon Bedrock AgentCore Code Interpreter 是 Deep Agents 的沙箱后端，支持在隔离的 MicroVM 环境中安全执行代码。

安装

pip

pip install langchain-agentcore-codeinterpreter

创建沙箱后端

有关用法、文件操作和生命周期详细信息，请参阅 沙箱指南。

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 配合使用

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

完成后请始终停止解释器以释放资源。

另见：沙箱。

---

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.