AI agent hosting
AI agent hosting on a server that never sleeps.
Agents, automations and coding assistants all need the same thing: a machine that stays on, holds your keys, and lives where you choose. A Lite is exactly that, by the hour, paid in crypto. Start from one-click templates for OpenClaw, n8n, Ollama with Open WebUI, and Coolify.
Launch offer: we double your first deposit. Deposit $100, spend $200. Your server is usually ready within 15 minutes; delete it any time.
- AI agentOpenClaw2 GB+ recommendedLite 2
- Coding agentClaude Code4 GB+ RAMLite 6
- Workflows with AI stepsn8nNo official figureLite 2 or 6
- Local model on CPUllama.cpp via OpenClaw8 GiB minimum for its smallest local modelLite 16
Plans and prices
Size the server to the job, not the hype.
All prices in USD, without VAT. Customers in the EU pay their country’s VAT on top. No setup fees, no contracts.
Each app’s own docs set the floor: OpenClaw 2 GB+, Claude Code 4 GB+, a local model 8 GiB or more. Billed per started hour, capped monthly.
| Plan | vCPU | RAM | Storage | Traffic | Hourly | Monthly | Keep a year | Action |
|---|---|---|---|---|---|---|---|---|
| Lite 2 | 2 | 2 GB | 40 GB NVMe | 1 TB | $0.006 | $4 | $40save $8 | Get it Lite 2 |
| Lite 6 | 6 | 6 GB | 100 GB NVMe | 2 TB | $0.012 | $8 | $80save $16 | Get it Lite 6 |
| Lite 8 | 8 | 8 GB | 160 GB NVMe | 3 TB | $0.018 | $12 | $120save $24 | Get it Lite 8 |
| Lite 16 | 16 | 16 GB | 320 GB NVMe | 4 TB | $0.03 | $20 | $220save $20 | Get it Lite 16 |
| Lite 32 | 16 | 32 GB | 640 GB NVMe | 6 TB | $0.06 | $40 | $440save $40 | Get it Lite 32 |
| Lite 64 | 24 | 64 GB | 1,280 GB NVMe | 8 TB | $0.12 | $80 | $880save $80 | Get it Lite 64 |
| Lite 96 | 32 | 96 GB | 1,920 GB NVMe | 10 TB | $0.18 | $120 | $1,320save $120 | Get it Lite 96 |
| Lite 128 | 40 | 128 GB | 2,560 GB NVMe | 12 TB | $0.24 | $160 | $1,760save $160 | Get it Lite 128 |
| Lite 192 | 48 | 192 GB | 3,840 GB NVMe | 14 TB | $0.36 | $240 | $2,640save $240 | Get it Lite 192 |
| Lite 256 | 64 | 256 GB | 5,120 GB NVMe | 16 TB | $0.48 | $320 | $3,520save $320 | Get it Lite 256 |
One-click templates
Four ways to start, already installed.
- OpenClawAn always-on agent gateway for your chat apps. Lite 2 and up. OpenClaw hosting.
- n8nWorkflows with AI steps, like Zapier on your own server. Its licence allows internal business and personal use.
- Ollama + Open WebUIA private chat with models that run on your server. Ollama listens only on localhost by default. On CPU, expect small models and slow answers.
- CoolifyDeploy MCP servers and other agent tools from Git, with HTTPS handled. Needs 2 cores, 2 GB and 10 GB.
Privacy
Where the model runs decides who sees your prompts.
| Setup | Where the model runs | Who sees your prompts | Server size |
|---|---|---|---|
| Agent + hosted model (OpenClaw, n8n) | At the model provider | You and the provider | Lite 2 or 6 |
| Coding agent (Claude Code) | At Anthropic | You and Anthropic | Lite 6 (4 GB+) |
| Local model (Ollama, llama.cpp) | On your Lite | Only you | Lite 16 and up |
A small CPU server makes your keys and logs yours. It doesn’t make a hosted model private. Only a local model keeps prompts on your server, and on CPU that means smaller models and slower answers.
MCP servers
Run MCP servers next to your agent, or publish them safely.
The Model Context Protocol is an open standard for connecting AI apps to your tools and data. It has two ways to run a server:
- stdio: beside the agentThe agent starts the MCP server as a subprocess. Host the agent and its MCP servers on the same Lite.
- HTTP: as a serviceAn independent process many clients can reach. The spec says it must check the Origin header and should require authentication. Coolify puts it behind HTTPS.
Claude Code
Claude Code on a server: what you need.
Anthropic supports Claude Code on Ubuntu 20.04+ and Debian 10+ with 4 GB of RAM or more, so start on Lite 6. It runs without a browser, and non-interactive mode lets scripts and other agents call it.
Two honest limits: you need a paid Anthropic plan or API key, and Anthropic’s supported-countries rule applies to your account wherever your server is.
What people use it for
Made for the work, not the brochure.
Assistants in chat
OpenClaw in Telegram or Slack, always on.
Automations with AI steps
n8n reads, sorts and replies while you sleep.
A private chatbot
Ollama and Open WebUI, prompts never leave the server.
Tools for your agents
MCP servers deployed from Git with HTTPS.
Coding agents
Claude Code on a Lite 6, working through the night.
Experiments
Try a new agent for an hour, delete it, pay for the hour.
Your use case is on the list? Lite 6 is $8 a month, or $0.012 an hour.
The rules
What you pay for, and what you don’t.
Every rule is on this page before you pay.
The server: per started hour at 0.15% of the monthly price, never more than the monthly price.
The apps: open source or source-available, each under its own licence.
Hosted models: paid to the provider directly. Your API keys live on your server, not in our billing.
Try it without the risk
The worst case is an hour and a few cents.
We’re new, so we don’t ask you to take our word for it. Here is what protects your money. Refund policy
- Delete any timeBilling stops at the hour you delete the server. No notice period, no cancellation form.
- A monthly capHourly charges stop at the plan’s monthly price. The rest of that month is free.
- The calculator is a promiseIf your bill is ever higher than our calculator for the same plan and hours, we refund the difference.
- Your cash credit is yoursUnused credit you paid for goes back to your wallet in crypto when you ask.
- Paused, not deletedRun out of credit and hourly servers pause, kept for 7 days. Top up and they come back.
- People who answerOur target is a first support reply within 20 minutes, 24/7, and 99.99% uptime with credit back if we miss. SLA
Deposit $100 and you have $200 to spend.
1. Create an account with an email address, a password and your country (for VAT). No name, no passport, no phone number.
2. Add funds from $20 in BNB, BTC, ETH, SOL, TRX, USDC, USDT, XRP or Monero (checked by hand). Each invoice shows one exact amount on one network, and the price holds for 30 minutes. A first deposit of $100 or more is matched 100% in bonus credit, up to $250; a smaller one gets +25%.
3. Your balance updates once the network confirms. You can close the page; we watch the chain for you. Coins, networks and confirmation times.
4. Deploy. Pick a country and an operating system. Your server is usually ready within 15 minutes, and billing starts only when it is ready.
Locations
Available in 15 countries.
BulgariaIn stock
GermanyIn stock
IcelandIn stock
JapanIn stock
LithuaniaIn stock
LuxembourgIn stock
MoldovaIn stock
NetherlandsIn stock
PakistanIn stock
RomaniaIn stock
SingaporeIn stock
SwedenIn stock
TurkeyIn stock
Ukraine*See note below
United StatesIn stock
* Ukraine: Service may be disrupted by the war. Keep backups in another country.
AI agent hosting FAQ
Questions before you buy.
Do I need a GPU to host AI agents?
No. Agents like OpenClaw and n8n call hosted models, so a CPU server is enough. Only running a model yourself needs much more memory.
Which template should I start with?
OpenClaw for a chat assistant, n8n for workflows, Ollama with Open WebUI for a private chatbot, Coolify for your own tools and MCP servers.
Is self-hosting cheaper than a ChatGPT or Claude subscription?
It depends on what you use. We haven’t found independent figures, so we won’t claim it. What you do get is control: your keys, your server, your country.
Can a CPU server run a local model?
Small ones, slowly. OpenClaw’s smallest local recipe needs 8 GiB, so plan on Lite 16 or larger.
Can I pay with crypto?
Yes: BTC, ETH, USDT, USDC, SOL, BNB, XRP or XMR, drawn from your balance by the hour. How crypto payments work.
The rest of the keep
Same account, same balance, six more ways to build.
Agents need a home.
From $4 a month, by the hour.
Top up in crypto (deposit $100, spend $200 on your first one), pick a country. Your server is usually ready within 15 minutes. No card, no ID, no contract.