Skip to main content

Cloud server with OpenClaw

OpenClaw Virtual Machine is a preconfigured cloud server with a personal AI assistant. The tool allows you to interact with the AI assistant via messengers to perform various tasks and automate workflows.

The image used to deploy the server includes:

  • OpenClaw — a personal AI assistant;

  • Ollama — a platform for locally downloading and running large language models (LLM);

  • Docker — a platform for running containerized applications;

  • Docker Compose — a tool for running multi-container applications in Docker;

  • nginx — a web server and reverse proxy;

  • drivers required for working with graphics processing units (GPU).

Before creating the server, read the software license agreements included with the image.

Functionality

  • performing tasks using the AI assistant via messengers and other supported applications;

  • collecting, processing, and providing information from various data sources;

  • automating workflows and running background tasks.

Minimum resource requirements

vCPU count2
RAM8 GB
Boot volume40 GB
GPURequired, with at least 24 GB of memory

Getting started with OpenClaw

For OpenClaw to work, the cloud server must be accessible from the internet. To do this, when creating a server, you must create a private subnet and attach a public floating IP address.

  1. Create a public floating IP address.

  2. Create a cloud server with OpenClaw.

  3. Run OpenClaw.

1. Create a public floating IP address

Create a public floating IP address so the cloud server with OpenClaw is accessible from the internet.

Use the Create a public floating IP address section of the Public floating IP addresses guide.

2. Create a cloud server with OpenClaw

  1. In the Control panel, on the top menu, click Products and select Cloud Servers.

  2. Click Create server.

  3. Fill in the blocks:

  4. Check the cloud server price.

  5. Click Create.

Name and placement

  1. Enter the server name. It will be set as the hostname in the operating system.

  2. Select a location where the server will be created. The available server configurations and resource costs depend on the location. You cannot change the location after the server is created.

Source

  1. Откройте вкладку Приложения.

  2. Select OpenClaw VM.

  3. Optional: if you need a different current or archived application version, select the required version in the Version field.

Configuration

Select a configuration from the GPU line starting 2 vCPU, RAM от 8 ГБ and размером загрузочного диска от 40 ГБ. Two types of server configurations are available for this line:

  • prebuilt configurations — configurations in the range with different specifications, in which the resource ratio is fixed;
  • custom configurations — configurations in which you can specify any resource ratio.

Configurations use different processors depending on the line and pool segment. You can customize the selected configuration. After the server is created, you will be able to change the configuration.

  1. Open the tab with the GPU range.

  2. Click Prebuilt.

  3. Optional: you can adjust the configuration if you are creating a server in a multi-zone pool segment ru-6 or pool segments ru-3b, ru-7a, and ru-7b:

    3.1. Разверните блок with описанием настроек конфигурации.

    3.2. Optional: выберите производителя процессора. Выбор производителя доступен не во всех пулах.

    3.3. Optional: if you do not want physical processor cores to be pinned to the cloud server vCPUs, uncheck the Dedicated Cores checkbox. For more details, see the Dedicated Cores tutorial.

    3.4. Optional: если для сервера with выделенными ядрами вы хотите выключить Hyper-Threading, снимите чекбокс Hyper-Threading (SMT).

    3.5. Optional: if you are creating a server with dedicated cores and want to host a multiprocessor server on a single NUMA node, select the Mandatory hosting on a single NUMA node. You can host a server with 4 vCPUs or more on a single NUMA node. If the cloud server resources cannot be placed on one node, it will not be created. For more information, see the Placing on a single NUMA node section of the Dedicated Cores tutorial.

  4. Select a GPU.

  5. Select a configuration.

  6. If both local and network volumes are available in the selected configuration, select the volume to be used as the boot volume:

    • локальный диск — отметьте чекбокс Локальный SSD NVMe диск. Сервер with локальным диском можно создать только из образов and приложений;
    • сетевой диск — не отмечайте чекбокс Локальный SSD NVMe диск.

    The amount of RAM allocated to the server may be less than the amount specified in the configuration — the operating system kernel reserves a portion of the RAM depending on the kernel version and distribution. You can check the allocated volume on the server using the sudo dmesg | grep Memory command.

Volumes

  1. If you did not check the Local SSD NVMe disk checkbox when setting up the configuration, the first specified network volume will be used as the server boot disk. To configure it:

    1.1. Выберите тип сетевого загрузочного диска.

    1.2. Укажите размер сетевого загрузочного диска in ГБ or ТБ. Учитывайте лимиты сетевых дисков on максимальный размер.

    1.3. If you selected the Universal v2 or SSD Fast v2 disk type, specify the total number of read and write operations in IOPS. After the disk is created, you can change the IOPS count — reduce or increase it. There is no limit on the number of IOPS changes.

  2. Optional: add an additional network volume of the server :

    2.1. Нажмите Добавить.

    2.2. Выберите тип сетевого диска.

    2.3. Specify the size of the network disk in GB or TB. Учитывайте лимиты сетевых дисков on максимальный размер.

    2.4. Если вы выбрали тип диска Универсальный v2 or SSD Быстрый v2, укажите общее количество операций чтения and записи in IOPS. После создания диска вы можете изменить количество IOPS — уменьшить or увеличить. Количество изменений IOPS не ограничено.

    After the server is created, you will be able to connect new additional volumes.

Internet

Configure public access to the server.

The cloud server will be added to a private subnet that is connected to a cloud router with 1:1 NAT and internet access. Access to and from the internet will be provided through the cloud router. The server will be accessible from the internet via a public floating IP address.

  1. В поле Подключение из интернета выберите тип доступа Публичный плавающий IP-адрес.

  2. Select a public floating IP address that you created in step 1.

Private network

The cloud server can be added to an existing or new private subnet.

  1. In the Subnet field, select a private subnet.

  2. Optional: in the IP address field, change the default IP address.

  3. В поле Роутер выберите существующий роутер or создайте новый.

    If the router is not connected to the internet, it will be automatically connected after the server is created.

Security

Select security groups to filter traffic on the server ports. Without security groups, traffic will be blocked. If this block is missing, traffic filtering (port security) is disabled in the server network. With traffic filtering disabled, all traffic is allowed.

Access

  1. Place an SSH key for the project on the server for secure connection:

    1.1. Если SSH-ключ для проекта не добавлен in облачную платформу, нажмите Добавить SSH-ключ, введите имя ключа, вставьте публичный ключ in формате OpenSSH and нажмите Добавить.

    1.2. If an SSH key for the project has been added to the cloud platform, select an existing key in the SSH key field. The SSH key is only available in the pool where it is stored.

  2. Optional: in поле Пароль для «root»:

    2.1. Скопируйте пароль пользователя root — пользователя with неограниченными правами on все действия над системой.

    2.2. Сохраните пароль in безопасном месте and не передавайте in открытом виде.

Additional settings

  1. If you are planning to create multiple servers and want to increase infrastructure fault tolerance, add the server to a placement group:

    1.1. Чтобы создать новую группу, in поле Группа размещения нажмите Создать.

    1.2. Выберите Новая группа and введите имя группы.

    1.3. Выберите политику размещения on разных хостах:

    • soft-anti-affinity — the system will try to place servers on different hosts. If there is no suitable host when creating the server, it will be created on the same host;
    • anti-affinity — servers in the group must be located on different hosts. If there is no suitable host when creating the server, the server will not be created.

    1.4. Если группа создана, in поле Группа размещения выберите группу размещения.

  2. Чтобы добавить дополнительную информацию or фильтровать серверы in списке, добавьте теги сервера. Автоматически добавляются теги операционной системы and конфигурации. Чтобы добавить новый тег, in поле Теги введите тег.

  3. Чтобы добавить скрипт, который выполнится with помощью агента cloud-init при первом запуске операционной системы, in блоке Автоматизация in поле User data:

    • откройте вкладку Текст and вставьте скрипт текстом;
    • or откройте вкладку Файл and загрузите файл со скриптом.

3. Run OpenClaw

  1. Open the http://<ip_address>:3000 page in your browser.

    Specify <ip_address> — the public floating IP address of the cloud server that you created in step 1.

  2. Enter the username — admin.

  3. Enter the password — the server UUID. You can copy it in the control panel: from the top menu, click Products → Cloud Servers → on the server card, click next to the UUID.

  4. Click Log in.