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

# Sandbox

> LangBot sandbox (Box Runtime) gives the built-in Agent an isolated environment to run commands and edit files safely.

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

| Tool    | Purpose                               |
| ------- | ------------------------------------- |
| `exec`  | Run shell commands inside the sandbox |
| `read`  | Read workspace files                  |
| `write` | Create or overwrite files             |
| `edit`  | Modify files via string replacement   |
| `glob`  | Find files by glob pattern            |
| `grep`  | Search file contents by regex         |

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

<Note>
  These tools target the built-in Agent. When using external runners such as Dify, n8n, Langflow, or Coze, use that platform's own tool mechanism.
</Note>

## 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.

| Scope              | Template                                          | Shared across                      |
| ------------------ | ------------------------------------------------- | ---------------------------------- |
| Global             | `{global}`                                        | All users share one sandbox        |
| Per chat (default) | `{launcher_type}_{launcher_id}`                   | Same group or DM shares one        |
| Per user           | `{launcher_type}_{launcher_id}_{sender_id}`       | Each member in a group is isolated |
| Per conversation   | `{launcher_type}_{launcher_id}_{conversation_id}` | Isolated by conversation           |
| Per message        | `{query_id}`                                      | Fully stateless                    |

<Warning>
  Commands within the same scope share filesystem state. Choose "per message" for full isolation.
</Warning>

## Lifecycle

| Condition                                      | Behavior                              |
| ---------------------------------------------- | ------------------------------------- |
| Idle for more than 5 minutes                   | Cleaned up automatically              |
| Box-managed processes running (e.g. stdio MCP) | Kept alive until those processes exit |
| `persistent: true` configured                  | Never cleaned up automatically        |

## Quick Start

1. **Prepare the backend**: install Docker locally, or pick Nsjail / E2B
2. **Edit `config.yaml`**:
   ```yaml theme={null}
   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](./config) 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](./config) — backends, security profiles, mounts, environment variables
* [Runtimes & Extensions Compared](./runtime-relationships) — how the sandbox, Skills, MCP, and plugins divide responsibilities