LocalSandbox
Added in: @mastra/core@1.1.0
Executes commands on the local system.
For interface details, see WorkspaceSandbox interface.
UsageDirect link to Usage
Add a LocalSandbox to a workspace and assign it to an agent. The agent can then execute shell commands as part of its tasks:
import { Agent } from '@mastra/core/agent'
import { Workspace, LocalFilesystem, LocalSandbox } from '@mastra/core/workspace'
const workspace = new Workspace({
filesystem: new LocalFilesystem({ basePath: './workspace' }),
sandbox: new LocalSandbox({
workingDirectory: './workspace',
env: {
NODE_ENV: 'development',
},
}),
})
const agent = new Agent({
id: 'dev-agent',
model: 'openai/gpt-4o',
workspace,
})
// The agent now has the execute_command tool available
const response = await agent.generate('Run npm install')
Auto-start behaviorDirect link to Auto-start behavior
LocalSandbox automatically starts on the first command execution if not already running. You can also explicitly start the sandbox by calling workspace.init() at application startup to avoid first-command latency.
Constructor parametersDirect link to Constructor parameters
id?:
workingDirectory?:
env?:
timeout?:
isolation?:
instructions?:
nativeSandbox?:
NativeSandboxConfigDirect link to nativesandboxconfig
Configuration options for native OS sandboxing (used with isolation: 'seatbelt' or 'bwrap').
allowNetwork?:
readOnlyPaths?:
readWritePaths?:
seatbeltProfilePath?:
bwrapArgs?:
allowSystemBinaries?:
PropertiesDirect link to Properties
id:
name:
provider:
status:
workingDirectory:
processes:
Path ResolutionDirect link to Path Resolution
Relative paths and execution contextDirect link to Relative paths and execution context
When you use a relative path for workingDirectory, it resolves from process.cwd(). In Mastra projects, cwd varies depending on how you run your code:
| Context | Working directory | ./workspace resolves to |
|---|---|---|
mastra dev | ./src/mastra/public/ | ./src/mastra/public/workspace |
mastra start | ./.mastra/output/ | ./.mastra/output/workspace |
| Direct script | Where you ran the command | Relative to that location |
This can cause confusion when the same relative path resolves to different locations.
Recommended: Use absolute pathsDirect link to Recommended: Use absolute paths
For consistent paths across all execution contexts, use an environment variable with an absolute path:
import { LocalSandbox } from '@mastra/core/workspace'
const sandbox = new LocalSandbox({
workingDirectory: process.env.WORKSPACE_PATH!,
})
Set WORKSPACE_PATH in your environment to an absolute path like /home/user/my-project/workspace. This ensures commands run from a consistent directory regardless of how you run your code.
Background processesDirect link to Background processes
LocalSandbox includes a built-in process manager for spawning and managing background processes. Processes run as child processes on the local machine using child_process.spawn.
const sandbox = new LocalSandbox({ workingDirectory: './workspace' })
await sandbox.start()
// Spawn a background process
const handle = await sandbox.processes.spawn('node server.js')
// Read output, send stdin, kill
console.log(handle.stdout)
await handle.sendStdin('input\n')
await handle.kill()
When native isolation is enabled (seatbelt or bwrap), spawned processes are also wrapped with the same isolation backend.
See SandboxProcessManager reference for the full API.
Static methodsDirect link to Static methods
detectIsolation()Direct link to detectisolation
Detect the best available isolation backend for the current platform.
const detection = LocalSandbox.detectIsolation()
// { backend: 'seatbelt', available: true, message: 'Seatbelt available on macOS' }
Environment isolationDirect link to Environment isolation
By default, LocalSandbox only includes PATH in the environment. This allows commands to run while preventing accidental exposure of API keys and secrets.
// Default: only PATH is available (commands work, secrets protected)
const secureSandbox = new LocalSandbox({
workingDirectory: './workspace',
})
// Explicit: pass specific variables
const sandbox = new LocalSandbox({
workingDirectory: './workspace',
env: {
NODE_ENV: 'development',
API_URL: 'https://api.example.com',
},
})
// Full access (use with caution)
const devSandbox = new LocalSandbox({
workingDirectory: './workspace',
env: process.env,
})
Native OS sandboxingDirect link to Native OS sandboxing
LocalSandbox supports native OS-level sandboxing for additional security:
- macOS: Uses Seatbelt (
sandbox-exec) for filesystem and network isolation - Linux: Uses Bubblewrap (
bwrap) for namespace isolation
// Detect the best available backend for this platform
const detection = LocalSandbox.detectIsolation()
console.log(detection)
// { backend: 'seatbelt', available: true, message: '...' }
// Enable native sandboxing
const sandbox = new LocalSandbox({
workingDirectory: './workspace',
isolation: 'seatbelt', // or 'bwrap' on Linux
nativeSandbox: {
allowNetwork: false, // Block network access (default)
readWritePaths: ['/tmp/extra'], // Additional writable paths
},
})
When isolation is enabled:
- File writes are restricted to the workspace directory (and configured paths)
- File reads are allowed everywhere (needed for system binaries)
- Network access is blocked by default
- Process isolation prevents affecting the host system
Sandbox profile locationDirect link to Sandbox profile location
When using seatbelt isolation on macOS, LocalSandbox generates a profile file in a .sandbox-profiles/ folder in process.cwd(), separate from the working directory:
project/
├── .sandbox/ # Default working directory (sandboxed)
│ └── ... files created by sandbox
├── .sandbox-profiles/ # Seatbelt profiles (outside sandbox)
│ └── seatbelt-a1b2c3d4.sb # Hash based on workspace + config
└── ... your project files
The profile filename is a hash of the workspace path and configuration, so sandboxes with identical settings share the same profile while different configurations get separate files. This prevents collisions when running multiple sandboxes concurrently.
This separation prevents sandboxed processes from reading or modifying their own security profiles. The profile is created when the sandbox starts and cleaned up when destroyed.