Before you start
Before you deploy your first AI agent, make sure you have the following ready. Having these prepared in advance makes the entire process take under 10 minutes from start to finish.
- A OneClickClaw account. If you have not signed in yet, see Creating Your Account. It takes 30 seconds with Google Sign-In.
- A plan in mind. You will select and pay for a plan during the deployment flow. If you have not decided yet, see Choosing a Plan to compare options.
- An AI provider API key. You need a working API key from at least one supported provider (Anthropic, OpenAI, OpenRouter, xAI, or any of the 25+ others). Get this from your provider's dashboard before you start. For help, see BYOK Explained.
- A messaging channel token (optional). If you want your agent to respond in Telegram or Discord right away, have your bot token ready. You can also set this up later from the Agent Control Panel.
Tip
The most common setup is: OneClickClaw Starter plan + an Anthropic API key + a Telegram bot token. This combination gives you a production- ready AI chatbot in your Telegram group for about €15/month plus a few dollars in AI provider costs.
The deployment flow
The Deploy Wizard guides you through the entire process step by step. Here is exactly what happens at each stage:
Choose a name for your instance
Give your deployment a memorable name (for example, "Support Bot" or "Community Agent"). This name appears in your dashboard and helps you identify the instance. It does not affect how your agent works or what users see. You can use letters, numbers, and spaces.
Instance Name Input
Text field: "My AI Agent" (placeholder)
Helper text: "This name is for your reference only"
Continue Button
[Continue to Plan Selection]
Select your plan
Choose the tier that fits your needs: Starter, Hobbyist, or Pro. You see all three options with their specs, pricing, and a brief description of who each plan is best for. Pick one and click Continue. You can change your plan later from your dashboard.
Complete checkout via Stripe
You are redirected to a secure Stripe checkout page. Enter your payment details (credit or debit card) and confirm the purchase. Stripe handles all payment processing. We never see or store your card details. Once payment is confirmed, provisioning starts automatically in the background.
Order Summary
Plan: Starter - €14.99/month
2 vCPU | 4 GB DDR4 RAM | 15 GB NVMe SSD
Payment Form
Card number, expiry, CVC (powered by Stripe)
[Pay €14.99] button
Wait for provisioning (~5 minutes)
After payment, your dedicated server is created, configured, and secured automatically. You see a real-time progress tracker on screen showing each step: server creation, software installation, SSL setup, and health check activation. The entire process typically takes about 10 minutes. You can stay on the page and watch, or close the tab and come back later.
Open your agent and pick a model
Once provisioning finishes, your agent opens in a new tab. OpenClaw shows its Model Setup page first: pair your ChatGPT subscription with a device code, pair xAI, or paste an API key, and it verifies the model before chat turns on. If you add a provider from the Models page instead, also pick a Default model there. Channels live under Settings, then Channels. From that moment your agent is live and responding to messages.
Warning
Your subscription starts immediately after checkout. There is no trial period. Make sure you have selected the right plan before completing payment. If you need to change plans later, you can do so from your dashboard.
What happens during provisioning
After payment, OneClickClaw creates and configures your dedicated server automatically. You do not need to do anything during this process. Here is what happens behind the scenes, in roughly 5 minutes:
- Server creation (~2 minutes). A new VPS is created in our EU datacenter (Denmark) with the CPU, RAM, and SSD specs matching your plan.
- Software installation (~2 minutes). Ubuntu is installed and hardened (firewall, SSH keys, automatic updates). Node.js, OpenClaw, and Nginx are installed and configured.
- SSL and connectivity (~1 minute). SSL certificates are provisioned so all traffic is encrypted. Health monitoring is enabled. The server reports back that it is ready.
Note
Provisioning takes about 10 minutes. Your server is being created, software installed, and SSL configured. If provisioning takes longer than 15 minutes, our support team is automatically alerted and will investigate. For more detail on what happens at each stage, see What Happens During Provisioning.
Creating server...
Spinner or checkmark | ~2 minutes
Installing software...
Spinner or checkmark | ~2 minutes
Configuring SSL & monitoring...
Spinner or checkmark | ~1 minute
Ready!
Green checkmark | "Your server is online"
Setup inside OpenClaw
Once provisioning completes, you land inside your agent. OpenClaw's own Model Setup page asks for your AI model: pair your ChatGPT or Codex subscription with a device code (ChatGPT Device Pairing under More sign-in options), pair an xAI account, or paste an API key. It sends one real request to the provider and turns conversations on only after a model answered. That takes about a minute if you have your key ready. A provider added from the Models page needs one more click: choose it in the Default model dropdown and save.
Chat channels are added under Settings, then Channels, each with its own guided setup. For a detailed walkthrough, see Set Up Your Agent Inside OpenClaw.
Tip
Web chat works with no channel at all: the Home page of your agent is a full chat. Add WhatsApp, Telegram or Discord whenever you want the agent on your phone.
What to do after deployment
Congratulations, your AI agent is live! Here are the most valuable things to explore next:
- Customize your agent's personality. Visit the Agent Control Panel to edit the system prompt. This is where you define how your agent behaves, what tone it uses, what topics it focuses on, and what it refuses to discuss. A well-crafted system prompt is the difference between a generic chatbot and a useful assistant.
- Add more channels. Connect additional Telegram groups or Discord servers from the Agent Control Panel. Your agent can serve multiple channels simultaneously with the same personality and configuration.
- Monitor performance. Your dashboard shows real-time metrics including CPU usage, memory consumption, and uptime. Keep an eye on these during the first few days to make sure your plan is a good fit for your workload.
- Experiment with models. Try different AI models to find the best balance of quality, speed, and cost for your use case. Switching models takes effect immediately, with no downtime.
- Read the docs. Browse the rest of this documentation to learn about advanced features like Setting Up Your AI Provider, Channel Management, and server monitoring.
Tip
Bookmark your dashboard URL. You can check on your agent, view metrics, and make configuration changes from any device with a web browser.