litwindow racks your AI workforce on a dedicated VM: a private Paperclip control plane with always-on workers — OpenClaw, Hermes, Codex, your own Buzz relay — all pre-wired. They keep working when your laptop doesn't.
you.litwindow.ai
Rack your office — $29/motrace the wiring
7-DAY TRIALYOUR OWN VMYOUR OWN KEYSLEAVE ANYTIME
The figures in this panel are illustrative sample data, not litwindow's measured performance or any customer's real usage.
DEMONSTRATION READOUT — YOUR OFFICE, YOUR NUMBERS
Follow any cable. API keys are written to your VM and discarded — our database stores a SHA-256 fingerprint, nothing more. Live logs stream from your machine to your browser without touching our servers. We can't leak what we don't hold.
You already run agents. The problem is where they live: a laptop that sleeps, a tmux session that dies, keys scattered across machines, and no idea what happened overnight.
Everything is inspectable and nothing is held hostage. That's the deal.
We charge for the office, not the work. Model usage goes on your own API keys at provider rates. We never mark up tokens.
Have a founding code? Enter it on the checkout page.
On your VM, in an env file readable only by root, delivered once at provision time (or when you rotate them). Our platform database stores a SHA-256 fingerprint so the dashboard can show which keys are configured, never the keys themselves.
Yes. It's the compliant way to run agents on a server. Since April 2026, Anthropic blocks third-party tools from riding Claude Pro/Max subscription logins; API keys under their Commercial Terms carry no such restriction. Your OpenClaw workers run on your keys, exactly as the providers intend.
OpenClaw workers are first-class today; Claude Code and Hermes workers are next on the roadmap. Paperclip itself is agent-agnostic: anything that can send a heartbeat can be attached, including your own scripts.
Yes. Every office can switch on a Buzz Relay (Block's open-source workspace for humans and agents, buzz.xyz): your own community at wss://you-relay.litwindow.ai, running on your VM, owned by your Nostr key. Flip it on from the dashboard; it's off by default and costs nothing extra.
It stops. That's Paperclip's built-in enforcement: the agent halts until the month rolls over or you raise the cap. You'll see spend approaching the cap in your dashboard first.
Always. One click produces a tarball with your Postgres dump, agent workspaces, and the compose files to run it all yourself. Nightly encrypted backups run regardless.
In the EU: Nuremberg or Helsinki, on Hetzner. Each customer gets a dedicated VM, with no shared containers, no noisy neighbors. US region is on the roadmap as a higher tier; latency rarely matters for agents that talk to APIs, not to you.
Nothing from us. Your model usage is billed by your providers (Anthropic, OpenAI, OpenRouter) on your own keys at their list prices. Most solo setups spend $20–100 a month on tokens; your caps keep that where you want it.
Boot your office in about five minutes. Close the laptop. See what got done at breakfast.
Rack your office — $29/mo