AI Sandboxes by Buddy - Isolated cloud machines for your AI coding agents
by•
Buddy Sandboxes give AI coding agents their own isolated Linux machines to build, run, test, and fix apps without touching your local setup. Each Sandbox has a persistent disk, root access, Docker, SSH, and a public URL. Create one per task, branch, or PR, then let your agents manage it through MCP, CLI, SDK, or API.
Replies
Why should I use a sandbox instead of running an agent locally?
@stryczekk Mainly for isolation and security. A Sandbox keeps the agent's work separate from your local machine, so it can install packages, run commands, and execute code without having direct access to your files or local environment. Agents also keep running when you shut down your computer, you can run multiple agents in separate Sandboxes, each with its own public URL, and use snapshots to roll back changes if something goes wrong.
Pawel's point about snapshotting dependencies and warmed caches makes a lot of sense. Rebuilding the same environment for every agent task would eat into the time you're trying to save.
@oleksii_sekundant Yeah, exactly. Agents are fast, but if you wait for the environment every time, you lose that, set it up once and reuse it.