What problem does it solve? Running untrusted or LLM-generated code safely requires isolated execution environments, and configuring containers, Durable Objects, and code interpreters on Cloudflare Workers involves many error-prone setup steps. ## Core Features & Use Cases - Sandboxed Command Execution: Run shell commands with exec() and capture stdout, stderr, and exit codes inside isolated containers. - Code Interpreter for AI: Execute LLM-generated Python, JavaScript, or TypeScript with runCode(), including rich outputs and persistent state across calls. - File and Port Management: Write, read, and list files in the sandbox, and expose HTTP services via preview URLs. - Use Case: Build an AI coding assistant that executes user-submitted Python scripts in isolated per-session sandboxes, returns results with charts, and destroys the container when the session ends. ## Quick Start Ask the AI to set up a Cloudflare Worker using @cloudflare/sandbox that runs a Python snippet in a sandbox and returns the output.