03:12 am — shift in progress

Your agents work the night shift.

Litwindow gives your AI agent workforce an office: a private Paperclip control plane with always-on OpenClaw workers, pre-wired on your own isolated VM at you.litwindow.ai. They keep working when your laptop doesn't.

7-day trial · your own VM · your own API keys · leave anytime

riya.litwindow.aiup 27d 14h
scout openclaw · research
drafter claude code · PRs
support openclaw · tickets
03:12:07 scoutfetched 14 competitor pages, summarizing
03:12:31 drafteropened PR #142: pricing page copy
03:13:02 supportreplied to 3 tickets, escalated 1 to you
03:13:40 paperclipbudget check: $31.20 / $50.00 ok
03:14:11 scoutheartbeat ok (2.1s)
monthly budget $31.20 / $50.00
Runs your agentsOpenClawClaude CodeHermesCodexanything with a heartbeat

07:30 am

Wake up to finished work, not dead processes.

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.

On your laptop

  • Agents die when the lid closes
  • A crashed process fails silently for days
  • API keys live in six dotfiles
  • Spend is a surprise on the invoice
  • Logs are wherever you last left them

In your litwindow office

  • Workers run 24/7 on a dedicated VM
  • Crashes restart themselves; you get an alert, not an outage
  • Keys are pushed to your VM once — we keep only fingerprints
  • Hard monthly budget caps per agent
  • Live logs in the dashboard, SSH if you want it

Built for operators, not spectators.

Everything is inspectable and nothing is held hostage. That's the deal.

wiring

Pre-wired on boot

Paperclip and your OpenClaw workers come already connected — heartbeats, invites, budgets. The wiring you'd otherwise do by hand is done before your first login.

custody

Your keys never live with us

API keys are written to your VM and discarded. Our database stores a fingerprint, nothing more. We can't leak what we don't hold.

spend

Hard budget caps

Set a monthly cap per agent. When it's hit, the agent stops — Paperclip's native enforcement, surfaced in your dashboard.

visibility

Logs you can actually read

Live log streaming for every worker, straight from your VM to your browser. Your logs never transit our servers.

resilience

It heals itself

Restart policies, health checks, and a watchdog agent. If something stays down, you get an email or Telegram ping — not a lost day.

exit

Leave anytime

One click exports your whole office — database dump, workspaces, compose files — as a tarball you can run anywhere.

Three minutes to a working office.

One form, one boot, and your agents clock in.

Claim your office

Pick a subdomain, choose EU or US, paste your API keys, set a budget. Import your existing OpenClaw workspace if you have one.

~1 min

We boot the building

A dedicated VM spins up from our golden image: Paperclip, your workers, TLS, backups — all wired.

~90 sec

Your agents clock in

Workers send their first heartbeat, pick up their roles, and get to work. You watch from the dashboard — or close the laptop. That's the point.

immediately

Flat pricing. Your tokens stay yours.

We charge for the office, not the work. Model usage goes on your own API keys at provider rates — we never mark up tokens.

Team

$79 /month
  • 3 always-on workers
  • Dedicated VM · 16 GB RAM
  • Everything in Solo
  • Telegram alerts
  • Priority support
Start 7-day trial

Agency

$149 /month · coming soon
  • Isolated org per client
  • Audit exports
  • White-label reports
Join the waitlist

Why bring your own keys? Because it keeps our incentives clean: we make the same money whether your agents think hard or sit idle, so we'll never nudge you toward burning tokens — and your model bill stays at provider list price.

Questions operators ask.

Where exactly do my API keys live?

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.

Is bring-your-own-keys even allowed?

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.

Which agents can I run?

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.

What happens when an agent hits its budget cap?

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.

Can I get my data out?

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.

Where is my VM?

In the EU — Nuremberg or Helsinki, on Hetzner. Each customer gets a dedicated VM — 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.

What does litwindow cost beyond the subscription?

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.

tonight

The night shift starts tonight.

Boot your office in three minutes. Close the laptop. See what got done at breakfast.

Start your office — $29/mo