• English

      • All-in-One Environment
      for AI Agents

      One Docker container with browser, terminal, filesystem, VSCode, Jupyter, and MCP Server — accessible via a single API/SDK.

      Browser/Terminal/Files/VSCode/Jupyter/MCP
      Get StartedGitHub
      Sandbox running
      sandbox.py
      1from agent_sandbox import Sandbox
      2
      3# Initialize client
      4client = Sandbox(base_url=f"${base_url}")
      5home_dir = client.sandbox.get_context().home_dir
      6
      7# Execute shell commands
      8result = client.shell.exec_command("ls -la")
      9print(result.data.output)
      10
      11# File operations
      12content = client.file.read_file(f"${home_dir}/.bashrc")
      13print(content.data.content)
      14
      15# Browser automation
      16screenshot = client.browser.screenshot()
      MCP Server active
      // capabilities

      Everything your agent needs,
      out of the box

      No more juggling multiple services. AIO Sandbox ships a complete, pre-wired environment in a single Docker container.

      Unified Environment

      One Docker container with shared filesystem. Files downloaded in the browser are instantly accessible in Terminal and VSCode.

      Out of the Box

      Built‑in VNC browser, VS Code, Jupyter, file manager, and terminal—accessible directly via API/SDK.

      Secure Execution

      Isolated Python and Node.js sandboxes. Safe code execution without system risks.

      Agent-Ready

      Pre-configured MCP Server with Browser, File, Terminal, Markdown, Ready-to-use for AI agents.

      Developer Friendly

      Cloud-based VSCode with persistent terminals, intelligent port forwarding(via `${Port}-${domain}/` or `/proxy`), and instant frontend/backend previews.

      Production Ready

      Enterprise-grade Docker deployment. Lightweight, scalable.