Vercel Sandbox Python SDK 1.0 is now available
Vercel Sandbox Python SDK 1.0 stabilizes its API and adds TypeScript parity for isolated code runs; upgrades from 0.x must account for command input and output switching to bytes.
The **Vercel Sandbox Python SDK 1.0** stabilizes its public API and reaches feature parity with the TypeScript SDK. It supports isolated code execution, automatic cleanup through context managers, and AnyIO-based async use with asyncio or Trio. Python applications that run agent-generated code or test agent changes can use the SDK to create and clean up sandboxes. Install with `uv add 'vercel-sandbox>=1.0'`; synchronous code uses `vercel.sandbox.sync`. Upgrades from 0.x include breaking changes: command input and output now use **bytes**. Review the 1.0 release notes and configure authentication before migrating.
No separate implication has been recorded yet.
The **Vercel Sandbox Python SDK 1.0** stabilizes its public API and reaches feature parity with the TypeScript SDK. It supports isolated code execution, automatic cleanup through context managers, and AnyIO-based async use with asyncio or Trio. Python applications that run agent-generated code or test agent changes can use the SDK to create and clean up sandboxes. Install with `uv add 'vercel-sandbox>=1.0'`; synchronous code uses `vercel.sandbox.sync`. Upgrades from 0.x include breaking changes: command input and output now use **bytes**. Review the 1.0 release notes and configure authentication before migrating.
The Python SDK 1.0 makes isolated sandbox execution available through a stable API with TypeScript parity, cleanup helpers, and asyncio or Trio support. Python agent workflows can use it for generated-code execution or change testing, but 0.x upgrades require adapting command input and output to bytes and setting up authentication.