What problem does it solve? Running untrusted or LLM-generated code safely requires isolated execution environments, and configuring Cloudflare's Sandbox SDK involves precise wrangler configuration, Durable Object bindings, and lifecycle management that are easy to get wrong. ## Core Features & Use Cases - Command and Code Execution: Run shell commands with exec() or execute Python, JavaScript, and TypeScript with runCode() for rich outputs and persistent interpreter state. - File and Port Management: Write, read, and list files inside sandboxes, and expose HTTP services through preview URLs. - Use Case: Build an AI code interpreter where an agent generates Python data-analysis code, executes it in an isolated per-session sandbox with pandas, and returns charts and results to the user. ## Quick Start Ask the agent to set up a Cloudflare Worker with the Sandbox SDK that runs Python code in an isolated sandbox and returns the execution result.