Dynamic, identity-aware, and secure Sandbox auth
As AI Large Language Models and harnesses like OpenCode and Claude Code become increasingly capable, we see more users kicking off sandboxed agents in response to chat messages, Kanban updates, vibe coding UIs, terminal sessions, GitHub comments, and more.
The sandbox is an important step beyond simple containers, because it gives you a few things:
Security: Any untrusted end user (or a rogue LLM) can run in the sandbox and not compromise the host machine or other sandboxes running alongside it. This is traditionally (but not always) accomplished with a microVM.
Speed: An end user should be able to pick up a new sandbox quickly and restore the state from a previously used one quickly.
Control: The trusted platform needs to be able to take actions within the untrusted domain of the sandbox. This might mean mounting files in the sandbox, or controlling which requests access it, or executing specific commands.
Today, we’re excited to add another key component of control to our Sandboxes and all Containers: outbound Workers. These are programmatic egress proxies that allow users running sandboxes to easily connect to different services, add observability, and, importantly for agents, add flexible Continue reading

