Open SourceNov 18, 2026 · 05:521 source

External sandboxes for coding agents

From simonwillison.net

Image: simonwillison.net
AI;DR

External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine. I worked on this project with Prime Radiant , the AI research lab behind Superpowers and other projects . My post on the Prime Radiant blog introduces the external sandbox pattern, where code executed by the agent runs inside a dedicated sandbox while the agent itself lives outside of that sandbox. To demonstrate this pattern we've released three sandbox server implementations: external-sandbox-v86 runs a Node.js server which then uses v86 to run Alpine Linux inside WebAssembly. external-sandbox-container is a Python web server which runs the sandbox in Alpine Linux inside an Apple Containers instance. external-sandbox-quicksand is another Python web server, this time using Microsoft's Quicksand sandboxing library, which bundles QEMU and Alpine Linux in a Python package! Each of these implementations offers the same localhost API.

Read the sourceSign in to suggest

Sources

#safety#open-source#openai#devtoolsMarkdown
Content history (2)
  • 2026-11-18 · Summary · vi · Replaced stored text
    Sử dụng các sandbox bên ngoài cho các coding agent.
    I've đang tìm hiểu những cách mới để sandbox mã nguồn được thực thi bởi các agent, tập tr…
  • 2026-11-18 · Title · vi · Replaced stored text
    Các sandbox bên ngoài dành cho coding agent
    External sandbox cho coding agent

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today