# Vercel Sandbox Python SDK 1.0 is now available

Source: [Vercel](https://vercel.com/changelog/vercel-sandbox-python-sdk-1-0-is-now-available)  
Feed7 permalink: https://feed7.dev/p/vercel-sandbox-python-sdk-1-0-is-now-available-1l3o8fc  
Published: 2026-11-16T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

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.

## Source Summary

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.

## Practical Implication

No separate implication recorded.

## Agent-Ready Context

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.

## Connected Context

Feed7 judgment across 1116 accumulated Signals:

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.

- [Vercel AI Gateway and Vercel Sandbox now available on Hermes Agent](https://feed7.dev/p/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent-04gyfsv) — Hermes demonstrates Vercel Sandbox as an isolated execution backend; the Python SDK provides a programmatic route for Python applications to use sandboxed execution.
- [Python 3.15 now available as a Vercel Managed Image](https://feed7.dev/p/python-3-15-now-available-as-a-vercel-managed-image-1diuokr) — The SDK supplies the Python sandbox interface, while this candidate adds an interpreter choice; tasks needing Python 3.15 must select that image explicitly.
- [Cursor Cloud Agents can now run in Vercel Sandbox](https://feed7.dev/p/run-cursor-cloud-agents-vercel-sandbox-0l3bo4n) — Both concern isolated execution in Vercel Sandbox, but Cursor Cloud Agents describe managed per-request workers while this SDK enables Python applications to create and clean up sandboxes directly.

## Context Map

- Layer: infra
- Domains: coding
- Topics: sandboxing, coding-agents

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
