OpenClaw 🦞

OpenClaw 🦞 (formerly Clawdbot, Moltbot) is a personal AI assistant that runs locally and connects to multiple messaging platforms via a WebSocket-based Gateway architecture.

⚠️ This template uses ghcr.io/openclaw/openclaw:2026.1.29. OpenClaw 🦞 is in rapid development, so there may be undiscovered bugs. Changing versions may also cause stability issues. If you encounter any issues, feel free to check the GitHub issues for solutions or to report new ones. For Zeabur platform-related issues, please contact Zeabur support.

---

Recommended Resources

OpenClaw 🦞 is CPU-intensive. Resource requirements may vary depending on the tools and features you use.

• Dedicated Server: 2+ vCPU, 2+ GB - highly recommended for stable performance

Usage

1. After deployment, a secure Gateway token is automatically generated for you
2. Find the pre-generated URL in the Instructions tab
3. Click the "Web UI (with token)" link to connect directly (token is included in URL)
4. When you see the OpenClaw 🦞 interface, deployment is complete
5. Go to the Chat page to test if your AI provider is working

For more details, see the official documentation.

Telegram Bot Setup

Getting your bot token from BotFather:

1. Open Telegram and search for @BotFather
2. Send /newbot to create a new bot
3. Follow the prompts to set a name and username for your bot
4. BotFather will send you a token (e.g., 123456789:ABCdefGHIjklMNOpqrsTUVwxyz)

Adding the token to Zeabur:

1. Go to your service's Environment Variables tab in Zeabur dashboard
2. Add TELEGRAM_BOT_TOKEN with your bot token
3. Restart the service

Pairing your Telegram account:

1. Send /start to your bot in Telegram
2. The bot will reply with a pairing code (e.g., JN4MSY23)
3. Approve the pairing using one of these methods:
   • Web Chat: In the OpenClaw web interface chat box, type openclaw pairing approve telegram <code>
   • Terminal: Open Command in Zeabur dashboard, run openclaw pairing approve telegram <code>
4. You'll see: Approved telegram sender <user-id>.
5. Now you can chat with the bot!

For other messaging platforms (WhatsApp, Discord, Slack, etc.), see the Channels documentation.

Changing the Default Model

The default model depends on your AI provider:

• Zeabur AI Hub: zeabur-ai/gpt-5-mini
• Anthropic API Key: anthropic/claude-opus-4-5

To change it:

• Chat commands: Use /models to view available models, /model <model-id> to switch (e.g., /model zeabur-ai/gpt-5-mini)
• Web UI: Go to Settings and select your preferred model

Configure More Models

See the Providers documentation for adding more AI models.

Additional Configuration

Beyond environment variables, you can configure OpenClaw via Web UI Settings or CLI commands. See the official documentation for more details.

Data Persistence

All data is stored under /home/node:

• /home/node/.openclaw - Configuration, sessions, devices, and credentials
• /home/node/.openclaw/workspace - Workspace and memory files

Browser Sandbox

If you need browser features (web browsing, screenshots, etc.), deploy the Browser Sandbox Template alongside OpenClaw.

Documentation

• GitHub: https://github.com/openclaw/openclaw