What problem does it solve? Running untrusted or LLM-generated code safely requires isolated execution environments, and wiring up containers, Durable Objects, and code interpreters on Cloudflare Workers involves many configuration details that are easy to get wrong. ## 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(), rich outputs, and persistent state across calls. - File and Port Management: Read, write, and list files in the sandbox, and expose HTTP services through preview URLs. - Use Case: Build an AI coding assistant that writes Python to /workspace, executes it in a per-user sandbox, returns charts and results, and destroys the container when the session ends. ## Quick Start Ask the assistant to create a Cloudflare Worker that uses the Sandbox SDK to run Python code in an isolated sandbox and return the result.
