Skip to content

Run AI agents on an always-on VM

Agents need a computer that stays on after you close the laptop: a disk for their memory and checkouts, a shell for their tools, and a way to reach you. An exe.dev VM is that computer. It is isolated from your own machine, private by default, and its LLM integration gives agents models without API keys on disk.

All 14 AI agents recipes

Claude Code AI agents A computer for Claude. A breather for your laptop. Run Claude Code on a remote server OpenClaw AI agents An AI sidekick with its own computer. Your laptop can take a nap. Host OpenClaw Codex AI agents A computer for Codex. An early night for your laptop. Run Codex on a remote server OpenCode AI agents Every model, one VM, and an agent that works while your laptop sleeps. Run OpenCode on a remote server Hermes Agent AI agents An agent that remembers you, on a computer that never sleeps. Self-host Hermes Agent Claude Agent SDK AI agents Claude Code as a library, with a whole computer to run on. Host a Claude Agent SDK app in a sandbox VM Pi Durable AI agents An agent that picks up where it left off, even after kill -9. Host a Pi Durable agent Agents AI agents Use exe.dev VMs as a sandbox Running Agents Claude Managed Agents AI agents Anthropic runs the agent. Each session's tools run on a VM of its own. Self-hosted sandbox for Claude Managed Agents Flue AI agents Run Flue agentic apps on exe.dev Flue Jev AI agents Call TypeSafe's decision model through an HTTP integration Jev Python SDK AI agents Full VMs as sandboxes. A with block creates one, runs your code, and deletes it. Create sandboxes from Python Remote MCP server AI agents Tools for all your agents, on a computer of their own. Private until you say. Host a remote MCP server TypeScript SDK AI agents Full VMs as sandboxes. Create, control, and destroy them from your code. Create sandboxes from TypeScript

Frequently asked questions

Do I need my own model API key?

No. Every exe.dev VM can reach models through the LLM integration at https://llm.int.exe.xyz, billed to your exe.dev account. You can also bring your own key or subscription.

Is it safe to give an agent a whole VM?

Safer than giving it your laptop. The VM is its own machine with its own disk; it holds only what you put there, and you can delete it and start over in seconds.

Does the agent keep running when I disconnect?

Yes. VMs stay on. Services run under systemd, and interactive sessions can live in tmux so you can reattach from anywhere.

Don't see what you need?

Anything that runs on Linux runs on exe.dev. Describe it, and Shelley sets it up on a new VM.

Describe a VM →