Agent Sandbox Python SDK

A Python SDK for the All-in-One Sandbox API, providing access to sandbox, shell, file, jupyter, nodejs, and mcp services.

Installation

pip install agent-sandbox

Usage

from agent_sandbox import Sandbox

client = Sandbox(base_url="http://localhost:8091")

ctx = client.sandbox.get_context()
print(ctx)

result = client.shell.exec_command(command="ls -la")
print(result)

Async Support

The SDK also provides async support through the AsyncSandbox class:

import asyncio
from agent_sandbox import AsyncSandbox

async def main():
    client = AsyncSandbox(base_url="http://localhost:8091")
    
    # Get sandbox context
    ctx = await client.sandbox.get_context()
    print(ctx)

    result = await client.shell.exec_command(command="ls -la")
    print(result)

asyncio.run(main())

Cloud Providers

Volcengine

Create a sandbox instance using the Volcengine provider. For more details, please refer to examples/provider_volcengine.py.

from __future__ import print_function

import os
import sys

# Add the parent directory to Python path so we can import agent_sandbox
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from agent_sandbox.providers import VolcengineProvider


def main():
    """
    Main function demonstrating Volcengine provider usage.
    """
    # Configuration - replace with your actual credentials
    access_key = os.getenv("VOLC_ACCESSKEY")
    secret_key = os.getenv("VOLC_SECRETKEY")
    region = os.getenv("VOLCENGINE_REGION", "cn-beijing")
    
    # Initialize the Volcengine provider
    provider = VolcengineProvider(
        access_key=access_key,
        secret_key=secret_key,
        region=region
    )
    
    print("=== Volcengine Sandbox Provider Example ===\n")
    
    function_id = "yatoczqh"
    
    print("1. Creating a sandbox...")
    sandbox_id = provider.create_sandbox(function_id=function_id)
    print(f"Create response: {sandbox_id}")


if __name__ == "__main__":
    main()

Features

Sandbox: Access sandbox environment information and installed packages
Shell: Execute shell commands with session management
File: Read, write, search, and manage files
Jupyter: Execute Python code in Jupyter kernels
Node.js: Execute JavaScript code in Node.js environment
MCP: Interact with Model Context Protocol servers

Requirements

Python 3.8+
httpx
pydantic
typing_extensions (for Python < 3.10)

Release files for agent-sandbox 0.0.30

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agent-sandbox 0.0.30
File	Size	Uploaded
agent_sandbox-0.0.30.tar.gz	111.8 kB	Mar 24, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for agent-sandbox 0.0.30
File	Interpreter	ABI	Platform	Reset
agent_sandbox-0.0.30-py2.py3-none-any.whl 243.6 kB Mar 24, 2026	Python 2, Python 3	none	any	Details

Total release size: 355.5 kB

Release files / agent_sandbox-0.0.30.tar.gz

Download URL	agent_sandbox-0.0.30.tar.gz
Size	111.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`29677beca8fabf9ee1ec7c0e5637d15ba37a7e1f58cc8deb82611772fdec43bb`
BLAKE2b-256 checksum How to use checksums	`325c94d924db07da1e4f0925dd593939e652bb45d60cc749756bcce2d302817d`
Upload date	Mar 24, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.9.6`

Release files / agent_sandbox-0.0.30-py2.py3-none-any.whl

Download URL	agent_sandbox-0.0.30-py2.py3-none-any.whl
Size	243.6 kB
Tags	Python 2 Python 3
SHA-256 checksum How to use checksums	`bbcca45a202abb7cd01162473f01f3218de5037745ef4fa539e617a3cc973896`
BLAKE2b-256 checksum How to use checksums	`5bbcb83d625cf8cb9611c379b452d60da47a26fb7ccfa6c56c63cde4e45214c2`
Upload date	Mar 24, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.9.6`