Examples

This page provides a collection of official guides and code examples for integrating the agent sandbox into your projects.
All-in-One (AIO) Sandbox Example

This guide demonstrates how to create and access an All-in-One (AIO) Sandbox via Agent-Sandbox, featuring multiple pre-installed tools including VNC, VSCode, Jupyter, and Terminal in one unified environment.

Coding Agent on Agent-Sandbox and LangGraph

This guide documents the complete setup and deployment of a coding agent that runs locally on Kubernetes using Kind (Kubernetes in Docker) with the agent-sandbox controller. The agent uses locally-cached transformer models to generate and execute Python code with automatic error correction.

Composing Sandbox with Network Policies

This guide documents the complete setup Sandbox with Network Policies that runs locally on Kubernetes using Kind (Kubernetes in Docker) with the agent-sandbox controller.

Isolated ML Workspaces with Agent-Sandbox

Isolated ML Workspaces with Agent-Sandbox

JupyterLab on Agent-Sandbox

Deploy single-user JupyterLab environments using Kubernetes agent-sandbox.

Manual PodDisruptionBudget (PDB) Configuration

This guide demonstrates how to protect Sandboxes from voluntary disruptions (e.g., node drains, cluster upgrades) using standard Kubernetes PodDisruptionBudget manifests, without relying on the controller’s automated disruption control.

Using Agent Sandbox as a Tool in Agent Development Kit (ADK)

This guide walks you through the process of creating a simple ADK agent that uses Agent Sandbox as a tool to execute Python code in a secure sandboxed environment.


Last modified February 10, 2026: Adding aliases and ensured to use hyphens in new urls (59b25fb)