Cloudflare Sandboxes

Execute untrusted or generated code on Cloudflare in Linux VMs (Containers) or isolated Dynamic Workers, via the Sandbox SDK.

Agent access

Cloudflare Agents SDK: SDK for stateful AI agents on Cloudflare with persistent state, real-time WebSockets, scheduled tasks and remote MCP servers.
Vercel Sandbox: Ephemeral compute primitive that runs untrusted or agent-generated code in isolated Linux microVMs.

Run agent-generated code safely in a sandbox (Guide): A defense-in-depth recipe for executing LLM-written or user-supplied code: pick an isolation boundary, lock down egress, keep secrets out, cap time and resources, and treat the output as untrusted.
Code sandboxes for AI agents (Comparison): E2B, Daytona, Modal, Vercel Sandbox, Cloudflare Sandboxes, Fly.io Sprites and microsandbox compared on isolation, pricing, free tier, lifetime, persistence, egress controls, SDKs, GPUs and self-hosting.