Back to Blog
openclaw Mar 1, 2026 3 min read

Deploy Openclaw — Your Personal AI Assistant Gateway — in Minutes

H

HowToDeploy Team

Lead Engineer @ howtodeploy

Deploy Openclaw — Your Personal AI Assistant Gateway — in Minutes

Openclaw is a local-first personal AI assistant gateway that connects to over 10 messaging channels — Telegram, Discord, Slack, WhatsApp, and more — with companion apps for macOS, iOS, and Android. It gives you a single, private AI assistant that lives on your own server and meets you wherever you already chat.

Self-hosting it normally means setting up a VPS, cloning the repo, configuring environment variables for each channel, managing the WebSocket control plane, and keeping everything running. With HowToDeploy, the whole thing takes a few minutes.

Why self-host Openclaw?

  • Privacy — your conversations never touch a third-party server. Your data, your rules.
  • Multi-channel — one AI assistant across Telegram, Discord, Slack, WhatsApp, and more.
  • Companion apps — connect from macOS, iOS, and Android alongside your messaging channels.
  • Full control — choose your own LLM provider, customize the system prompt, and tune behavior.

Prerequisites

Before you start, you'll need:

  • A HowToDeploy account (sign up free)
  • A cloud provider API key (DigitalOcean, Hetzner, Vultr, Linode, or AWS)
  • An Anthropic API key for the LLM backend
  • A Telegram Bot Token (create one via @BotFather)

Step 1: Connect your cloud provider

Go to Settings → Cloud Providers and paste your API key for whichever provider you prefer.

Tip: Openclaw runs comfortably on a small server. Hetzner's CX21 or DigitalOcean's $12/month droplet is more than enough.

Step 2: Deploy Openclaw

Head to the Dashboard and find Openclaw in the AI Agents section of the app catalog. Click the card to open the deploy form.

You'll need to fill in two fields:

  • Anthropic API Key — the key Openclaw uses to call Claude for AI responses
  • Telegram Bot Token — connects your Telegram bot to Openclaw

That's it. Server size, region, and system dependencies are all pre-configured.

Step 3: Connect more channels (optional)

Want to reach your assistant on Discord, Slack, or WhatsApp too? Expand Advanced Settings on the deploy form and add:

You can also add these later from your deployment settings — no need to set everything up on day one.

Step 4: Start chatting

Once deployment completes, your Openclaw instance is live. Open Telegram, find your bot, and send a message. Your private AI assistant is ready.

To connect from your phone or laptop, download the Openclaw companion app and point it at your server's WebSocket endpoint.

What's included

Every Openclaw deployment includes:

  • Self-contained runtime — no external database dependencies
  • WebSocket control plane — real-time communication with companion apps
  • 10+ channel integrations — Telegram, Discord, Slack, WhatsApp, and more
  • Full SSH access — your server, your data, your rules

Pricing

You pay your cloud provider directly for the server (typically $6-12/month). HowToDeploy charges a small monthly management fee to handle monitoring and support.

Start with a 7-day free trial — no credit card required.


Ready to deploy your personal AI assistant? Deploy Openclaw now →