Moltbot (formerly Clawdbot) Comprehensive Installation Guide: One-Click Script Deployment & Telegram Integration

Moltbot (formerly Clawdbot) is a powerful open-source AI assistant that can run locally and interact with you via various messaging platforms (like Telegram, Discord).

This article demonstrates the simplest script-based installation method, teaching you how to integrate it with Telegram while using Google Gemini’s free quota to enhance the experience.

1. Environment Preparation

Before starting the installation, please ensure your server or local environment meets the following minimum requirements. Although the script handles some dependencies, pre-checking avoids many errors.

• Node.js: v22 or higher
• npm: v10 or higher
• Git: v2.34 or higher
• pnpm: v10 or higher (Optional, Recommended)

2. One-Click Script Installation

Open your terminal and run the official one-click installation script:

curl -fsSL --proto '=https' --tlsv1.2 https://molt.bot/install.sh | bash

During the installation, the script will guide you through an interactive configuration. Please follow these steps:

2.1 Risk Confirmation

First, you will be warned that the software requires powerful permissions (such as file read/write, command execution). Please read carefully, and type Yes after confirming the risks.

2.2 Select Base Model

Moltbot needs a “brain” to think. You can choose OpenAI (GPT-4/o1), Anthropic (Claude 3.5 Sonnet), etc.

• Here we demonstrate using an OpenAI Key.
• Select the corresponding model version, such as gpt-4o or gpt-5.2 (if released).

2.3 System Installation Process

The script will automatically download necessary components and build the environment.

3. Configure Telegram Bot

Near the end of the installation, the script will ask which messaging platform you wish to integrate.

1. Select Telegram.
2. The script will prompt you to enter the Telegram Bot Token.

How to get a Token?

• Search for @BotFather in Telegram.
• Send the /newbot command.
• Follow the prompts to enter a name and username for your bot.
• Copy the long string under Use this token to access the HTTP API: and paste it into the terminal.

4. Install Skills (Optional): Free Gemini Integration

Moltbot supports extended skills (Skills/Stills). Here we recommend installing the Gemini plugin, as Google currently provides a monthly free API quota, which is perfect as a backup or enhanced model.

• Tutorial reference: Get $10 Free Credit from Google AI Studio
• Select to install Gemini related components during the installation guide, and enter the obtained API Key.

5. Start Service & Dashboard

Once all configurations are complete, you can start Moltbot’s Web management interface with the following command:

clawdbot dashboard --no-open

(Note: The --no-open parameter prevents attempting to open a browser on a headless server)

After successful startup, you can access the Dashboard via a browser to view conversation history or perform debugging.

6. Telegram Hands-on Experience

After the service starts, you can happily chat with the Bot you just created on Telegram.

Common Interaction Commands

• Direct Conversation: Chat directly just like with a real person.
  • Example: “Write a Python script to scrape webpage titles for me.”
• Context Memory: Moltbot remembers previous conversation content, and you can ask follow-up questions at any time.
  • Example: “Can you explain that function in the code you just wrote in detail?”
• Multimodal Support: If you configured a vision-supported model like Gemini, you can send images directly to the Bot for analysis.

Tips

1. Privacy Protection: By default, Moltbot might respond to everyone who messages it. It is recommended to restrict replies to only your own Telegram ID via ALLOWED_USER_IDS in the configuration file.
2. Background Running: On a server, it is recommended to use nohup or pm2 to keep the clawdbot process running in the background, preventing the service from stopping when SSH disconnects.
   • Command Example: nohup clawdbot dashboard --no-open > moltbot.log 2>&1 &

Now, you own a 24/7 standby, completely private AI programming assistant. Enjoy exploring!