本页还没有译文

本页 8 段还没译成한국어，下面显示的是英文原文。

Sandbox integrations

还没翻译译自英文（docs.langchain.com）本页 8 段都还没译

Sandboxes provide isolated execution environments for running agent-generated code safely. Learn more about sandboxes.

Integration components

Typical retrieval flow: Document loaders → Text splitters → Embedding models → Vector stores → Retrievers → Chat models
Agent capabilities: Tools, Middleware
Execution and state: Sandboxes (this page), Backends, Checkpointers, Stores

Integration	Downloads
`DaytonaSandbox`
`ModalSandbox`
`AgentCoreSandbox`
`VercelSandbox`
`E2BSandbox`
`RunloopSandbox`
`OpenSandboxBackend`
`OpenShellSandbox`
`OpsenSandbox`
`LizardSandbox`
`KubernetesSandbox`
`RuntimeSandbox`
`NonoSandbox`
`IsloSandbox`
`NovitaSandbox`
`UpstashBoxSandbox`
`BaponiSandbox`
`Leap0Sandbox`
`SuperserveSandbox`
`LangSmith sandbox`	N/A

If you'd like to contribute a sandbox, see Implement a sandbox integration.

AI 翻译查看英文原文