How to Get Started with OpenClaw on Cloudways

OpenClaw on Cloudways allows you to deploy and run an AI agent on managed infrastructure without manually setting up servers, containers, SSL certificates, or runtime environments.

It is part of the Cloudways Managed AI Agents, which is designed to help users launch AI agents in a simpler and more managed way.

OpenClaw is the first agent available in this Managed AI Agents lineup. It helps users create and run AI-powered workflows that can connect with tools, data sources, and communication channels.

This means you can use OpenClaw to build assistants that help with tasks such as responding to messages, managing workflows, connecting with third-party services, and automating multi-step processes.

With OpenClaw on Cloudways, Cloudways manages the infrastructure layer for you. This includes provisioning the server, deploying the OpenClaw container, installing and renewing SSL/TLS certificates, and handling platform-level updates.

You remain in control of the agent itself, including its skills, nodes, environment variables, workflows, and LLM provider connections.

This guide explains what OpenClaw is, what you can use it for, what you need before getting started, and how to launch and access your OpenClaw agent from the Cloudways Platform.

OpenClaw is an open-source personal AI agent platform. An AI agent is a software assistant that can understand instructions, use connected tools, and perform tasks based on the workflows you configure. Instead of only answering a question, an AI agent can be set up to complete actions, follow steps, interact with other services, and support automation.

OpenClaw runs on its own infrastructure on Cloudways. This gives you more control over how your agent is hosted, where it is hosted, and how it is configured. You can connect OpenClaw with your preferred LLM provider, configure your own workflows, and decide how your agent interacts with your tools and users.

An LLM provider is the company or service that provides the AI model used by your agent. Examples include OpenAI, Anthropic, and Google. OpenClaw uses your connected LLM provider to understand prompts, process instructions, and generate responses or actions.

Managed AI Agents is a Cloudways product line that helps users deploy AI agents on dedicated infrastructure without managing the technical setup themselves.

In a traditional self-hosted setup, users may need to manually configure a server, install Docker, set up SSL certificates, manage updates, and troubleshoot the runtime environment.

These steps can be difficult for non-technical users and time-consuming even for experienced developers.

Cloudways simplifies this process by managing the infrastructure required to run the agent. You choose the agent, select the required server size and region, and launch it from the Cloudways Platform.

Cloudways handles the server provisioning and OpenClaw deployment, while you focus on configuring and using the agent.

OpenClaw is the first Managed Agent available on Cloudways. More agents may be added to this in the future.

OpenClaw can help you build and run automated AI workflows. A workflow is a set of steps or actions that your agent follows to complete a task.

For example, a workflow can help answer customer questions, collect information, perform research, prepare content, manage communication, or connect with external tools.

You can use OpenClaw for tasks such as responding to messages on channels like WhatsApp or Slack, automating research, creating content, managing emails, connecting to third-party tools, and running multi-step tasks with less manual effort.

OpenClaw can also be useful for agencies, developers, and businesses that want to create an autonomous operations layer for websites, stores, apps, or internal processes.

For example, an agency may use an agent to help with client reporting, uptime checks, performance audits, onboarding workflows, domain-related tasks, or other repeated operational activities.

OpenClaw on Cloudways is designed for users who want the benefits and control of AI agent hosting without the operational complexity of self-hosting.

If you deploy OpenClaw on a raw VPS, you may need to manage Docker, SSL, reverse proxy configuration, server maintenance, and updates yourself. Cloudways removes much of this manual infrastructure work.

You can launch OpenClaw from the Cloudways Platform, choose the server size based on your expected workload, select the hosting region that best suits your users or data needs, and access the OpenClaw dashboard directly from the Cloudways UI.

This setup is especially useful for users who already trust Cloudways for application hosting, for those who want control and flexibility, and want to keep their agent hosting under the same platform, billing system, user interface, and support experience.

When you launch OpenClaw on Cloudways, Cloudways creates a dedicated droplet for your agent. A droplet is a virtual server that provides the compute, memory, storage, and bandwidth needed to run your agent.

OpenClaw is installed as a container inside that dedicated droplet. A container is a packaged environment that includes the software and dependencies required to run an application.

This allows OpenClaw to run in an isolated and consistent environment.

When launching OpenClaw, you need to choose a droplet tier based on your expected workload. A workload means the amount of activity your agent is expected to handle. A simple workflow with low usage may need fewer resources, while a more complex workflow or higher traffic may require more CPU, memory, storage, and bandwidth.

The available droplet tiers are:

OpenClaw requires a minimum of 2 GB RAM. If you are not sure which tier to choose, start with the lowest available tier and scale up later as your workflow complexity or usage grows.

Before launching OpenClaw on Cloudways, make sure you have an active paid Cloudways account. OpenClaw is not available on trial accounts, so you need to upgrade to a paid account before you can access and launch OpenClaw from the Cloudways Platform.

You also need an API key from your preferred LLM provider, such as OpenAI, Anthropic, or Google. An API key is a secure access key that allows OpenClaw to connect with your selected AI model provider. You will add this key during or after the setup process so OpenClaw can use the selected AI model.

Important: LLM usage is billed directly by your LLM provider and is separate from your Cloudways subscription. while your LLM provider may charge you separately for AI model usage. You are responsible for monitoring your LLM API usage and managing any costs from your provider.

Follow these steps to launch and configure your OpenClaw agent from the Cloudways Platform.

A region represents the physical data center location where your agent runs. It is recommended to select a region closest to your users for better response times. You can also select a region based on your data residency or compliance requirements.

Choose an instance size based on your expected workload and agent requirements.

The available instance sizes are:

For basic usage or testing, the lowest instance size may be sufficient. For complex workflows, multiple tasks, or higher usage, choose an instance with more CPU and memory resources.

An LLM (Large Language Model) provider powers your OpenClaw agent by providing the AI model used to process instructions and generate responses.

An API key is a secure authentication key that allows OpenClaw to connect with your LLM provider.

If you do not have an API key, click Get API Key to create one from your selected provider.

Once your OpenClaw agent is successfully created, it will appear under the Managed AI Agents section.

You can perform the following actions:

After launching your OpenClaw agent, you can manage your LLM provider connection from the OpenClaw dashboard.

The LLM provider connection allows your agent to use the selected AI model for processing requests and completing tasks.

If you have not added your LLM Key in the first step, you can also update your API key anytime from LLM Provider section inside AI Agents tab.

You can interact with your OpenClaw agent directly from the OpenClaw dashboard. Connecting a messaging channel is optional.

Messaging channels allow users or teams to interact with the agent through platforms they already use. Available messaging channels may include:

To connect a messaging channel:

For example, connecting Slack allows your team members to interact with the agent from Slack conversations, while WhatsApp integration allows users to communicate with your agent through WhatsApp.

If you do not connect a messaging channel, you can continue managing and interacting with your agent through the OpenClaw dashboard.

After your OpenClaw agent is deployed, you can access the OpenClaw dashboard directly from the Cloudways Platform.

The OpenClaw dashboard allows you to:

The dashboard can be accessed using the Open Agent option from the Managed AI Agents section.

Device pairing is OpenClaw's way of confirming that any device trying to reach your agent's dashboard is one you actually control. You approve each new browser, phone, or computer once, and only approved devices can access your agent after that.

It is needed because your OpenClaw agent is reachable over the internet. Without pairing, anyone who knew or guessed the URL could log in and control your agent, your LLM keys, and connected channels like WhatsApp or Slack. Pairing closes that gap.

The first time you access your OpenClaw dashboard from a Linux/MacOS device, you will need to pair that device.

This is a one-time step per device.

Copy the Gateway Token/Access Key as shown below.

To access the OpenClaw Control UI from a Windows device, you need to approve your device by connecting to your OpenClaw server through SSH and running the device approval command.

Follow the steps below to pair your device.

Before connecting through SSH, collect the required SSH credentials from your OpenClaw dashboard.

Under the SSH Credentials section, note down the following details:

You will use these details to connect to your OpenClaw server using an SSH client.

Windows users can use PuTTY to establish an SSH connection with the OpenClaw server.

When connecting to the server for the first time, PuTTY displays a security warning asking you to verify the server host key.

This confirmation is required only the first time you connect to the server.

After accepting the host key, PuTTY opens the SSH terminal.

After successful authentication, you will be connected to your OpenClaw server.

After connecting to your OpenClaw server through SSH, run the following command:

Replace <request-id> with the device pairing request ID shown in your OpenClaw Control UI.

Example:

This approves the device request and allows your browser to access the OpenClaw Control UI.

Once your OpenClaw agent is active, you can manage your agent configuration and supporting infrastructure.

You can manage:

For advanced configuration, file transfers, or troubleshooting, SSH access is available for the underlying server.

SSH (Secure Shell) allows secure command-line access to your server, while SFTP (Secure File Transfer Protocol) allows secure file transfers between your system and the server.

These options are recommended for advanced users or technical teams who need additional control over their OpenClaw environment.

Cloudways manages the infrastructure layer required to run OpenClaw. This includes droplet provisioning, stack setup, OpenClaw container deployment, OpenClaw installation, SSL/TLS certificate installation and renewal, OpenClaw versioning, and platform-level updates.

SSL/TLS certificates help secure communication between the browser and your OpenClaw instance. Cloudways handles installation and renewal so you do not need to configure certificates manually.

Cloudways also manages the deployment process so you do not need to install Docker, configure the server manually, or manage the runtime stack yourself.

You manage the agent layer. This includes selecting the droplet size and region, connecting your LLM provider API key, securing your API keys and environment variables, defining your agent’s skills and nodes, and controlling how your agent behaves.

You are also responsible for managing your LLM provider usage and costs. Since LLM billing is handled directly by your model provider, you should monitor usage from the provider dashboard and configure any usage limits or billing alerts available from that provider.

The responsibility for OpenClaw on Cloudways is divided between Cloudways and the customer.

Cloudways handles the infrastructure layer. This includes provisioning, deployment, SSL/TLS, platform updates, and the managed setup required to run OpenClaw.

The customer handles the agent layer. This includes selecting the required plan, connecting the LLM provider, managing agent logic, securing keys, and configuring workflows.

OpenClaw on Cloudways gives you a managed way to deploy and run an AI agent without handling the infrastructure setup yourself.

Cloudways manages the server, deployment, SSL/TLS, and platform-level maintenance, while you stay in control of the agent configuration, workflows, LLM provider connection, and behavior.

This makes OpenClaw useful for developers, agencies, businesses, and AI builders who want to run AI agents with less operational overhead and more control over their agents.

That’s it! We hope this article was helpful.

If you need assistance, feel free to:

We're here 24/7 to help you!