Skip to main content
Before you connect OpenClaw to Fhddos, you need a working OpenClaw installation with its gateway process running. This page walks you through every step — from checking Node.js prerequisites to launching the Web UI — so you have a solid foundation before adding model provider configuration.
This page covers the essential install and launch flow. For the full OpenClaw reference, see the OpenClaw GitHub repository.

​
Prerequisites

Confirm your environment meets the following requirements before installing.
RequirementMinimum version / note
Operating systemmacOS, Linux, or Windows (WSL2 recommended)
Node.js≥ 22
Package managernpm, pnpm, or bun
Check your current Node.js version: 
node -v
If your version is below 22, install Node 22 via nvm: 
# Install nvm (Linux / macOS)
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash
source ~/.bashrc  # or ~/.zshrc

# Install and activate Node 22
nvm install 22
nvm use 22

​
Install the OpenClaw CLI

Install the latest version globally: 
npm install -g openclaw@latest
Verify the installation succeeded: 
openclaw --version
You should see a version string printed to the terminal. If you see command not found, check that your global npm bin directory is on your PATH.

​
Run the onboarding wizard

Launch the interactive wizard and install the background daemon in one command: 
openclaw onboard --install-daemon
The wizard automatically:
  • Creates the OpenClaw working directory at ~/.openclaw
  • Guides you through model provider configuration (you can skip this now and configure Fhddos afterward)
  • Sets default model and session parameters
  • Configures communication channels (WhatsApp, Telegram, Slack, Lark/Feishu, WebChat, etc.)
  • Installs and starts the gateway daemon
If you plan to use Fhddos as your model provider, skip the model configuration step in the wizard. Configure it directly by following Connect to Fhddos instead.

​
Start the gateway manually (debugging)

For development or troubleshooting, start the gateway in the foreground with verbose logging: 
openclaw gateway --port 18789 --verbose
  • Default control plane address: ws://127.0.0.1:18789
  • The --verbose flag prints detailed logs to help diagnose connection or configuration issues.

​
Basic usage

Once the gateway is running, try these commands to confirm everything works end-to-end.

​
Send a message from the terminal

openclaw message send \
  --to +1234567890 \
  --message "Hello from OpenClaw"
The --to value format depends on your configured channel — phone number, chat ID, channel name, etc.

​
Run an agent conversation

openclaw agent --message "Give me a simple travel checklist"
This routes the prompt through your configured default model, making it a quick smoke-test for model connectivity.

​
Open the Web UI

After the gateway starts, open the URL printed in the logs (usually http://127.0.0.1:18789) in your browser. From the Web UI you can:
  • Dashboard — view gateway status, nodes, and channel health
  • WebChat — chat directly in the browser
  • Channels — manage channel tokens and webhooks
  • Models — inspect and adjust model provider settings

​
Advanced deployment

git clone https://github.com/openclaw/openclaw.git
cd openclaw
pnpm install
pnpm ui:build
pnpm build
pnpm openclaw onboard --install-daemon
pnpm gateway:watch  # auto-reloads on code changes

git clone https://github.com/openclaw/openclaw.git
cd openclaw

# Option 1 — one-command setup script
./docker-setup.sh

# Option 2 — docker-compose
docker-compose up -d
After startup, access the gateway and Web UI on the ports exposed in your docker-compose.yml.

​
Troubleshooting

  • Confirm npm install -g openclaw@latest completed without errors.
  • Run npm bin -g to find the global bin path, then add it to your PATH.
Install Node 22 or later using nvm (see the prerequisites section above), then reinstall the OpenClaw CLI.
Run the built-in diagnostics command:
openclaw doctor
Follow the output prompts to check configuration, file permissions, and network access.
Re-run openclaw onboard and review the token, certificate, and webhook settings for the affected channel.

​
Next step

Connect to Fhddos

Configure Fhddos as your model provider and start routing AI calls through the Fhddos gateway.