Sandbox

The sandbox gives the built-in Agent an isolated execution environment: run commands, read and write files, and host long-lived processes. Everyday Agent use cases (data processing, file operations, running user code, hosting stdio MCP) all rely on it. Once the sandbox is enabled, the built-in Agent automatically gains six tools — no need to wire each one into the pipeline.

​

Built-in Tools

exec runs inside the sandbox container; the other five operate directly on the host directory mapped to /workspace.

​

Sandbox Scope

The pipeline’s AI configuration lets you choose how the sandbox is shared across messages. The default “per chat” works for most cases.

​

Lifecycle

​

Quick Start

1. Prepare the backend: install Docker locally, or pick Nsjail / E2B
2. Edit config.yaml:
   box:
     enabled: true
     backend: 'local'
     local:
       host_root: './data/box'
   
3. Start LangBot: the sandbox is enabled automatically
4. In the pipeline, select the built-in Agent plus a model that supports function calling

The Agent will then automatically receive the six tools. See Sandbox Configuration for details.

​

Disabling the Sandbox

Set box.enabled: false. Everything that depends on the sandbox (built-in tools, Skill create/edit/activate, stdio MCP) is disabled together; MCP servers in http/sse mode are unaffected.

​

Next Steps

• Sandbox Configuration — backends, security profiles, mounts, environment variables
• Runtimes & Extensions Compared — how the sandbox, Skills, MCP, and plugins divide responsibilities