Skip to content
InfoNewsLLM-specific

External sandboxes for coding agents

Published
Record updated
View JSON

Summary

Simon Willison, working with Prime Radiant, describes an external sandbox pattern in which code run by a coding agent executes inside a separate sandbox while the agent itself stays outside it. Three sandbox server implementations are released, external-sandbox-v86, external-sandbox-container and external-sandbox-quicksand, each exposing the same localhost API that Pi, Claude Code or Codex can call. The sandboxes also offer an optional HTTP/HTTPS allow-list proxy and a credential replacement mechanism so the agent can make authenticated calls without holding the secret.