Nanobot: the Lightweight Alternative to OpenClaw for Creating Your AI Agent

Nanobot: A Lightweight Alternative to OpenClaw

In my quest for a simpler solution than OpenClaw for everyday use, I discovered Nanobot. It stands out for its lightweight nature and ease of setup, particularly for a quick connection to WhatsApp. I've noticed a growing interest in Nanobot on platforms like YouTube, which prompted me to explore it further.

This article will guide you through the architecture of Nanobot and how it works. We will then cover the six essential steps for installation, configuration, and connection to WhatsApp, enabling you to create a 24/7 operational artificial intelligence (AI) agent for various tasks.

Why Choose Nanobot for Your First AI Agent

Nanobot is ideal for those starting out in creating AI agents. It simplifies the setup while offering essential features for practical use. In addition to WhatsApp, it can connect to Telegram, Slack, Discord, Feishu, QQ, and even emails. It also supports a variety of model providers and model context protocol (MCP) tool servers, helping novices understand the structure of an agent without being overwhelmed by complexity.

Nanobot also distinguishes itself from OpenClaw with its practical integrations and immediate utility. Beyond messaging channels, it allows for tool calls, web searches, scheduled tasks, voice transcription, real-time progress streaming, and offers multiple provider options. This makes it an effective personal assistant rather than just a simple demonstration project.

Step 1: Installing uv

The first step is to install uv, a tool that Nanobot uses to manage the Python environment and its dependencies. After installation, it is crucial to verify that everything is working correctly by confirming the installed version.

curl -LsSf https://astral.sh/uv/install.sh | sh

To check the installation, run:

uv 0.10.9 (f675560f3 2026-03-06)

Step 2: Installing Nanobot

Once uv is in place, use it to install the Nanobot package. This adds the command-line interface (CLI) for Nanobot, allowing you to launch it directly from the terminal.

uv tool install nanobot-ai

Step 3: Initializing Your Nanobot Project

Next, run the integration command to initialize Nanobot. This creates the basic local configuration, including the default configuration directory at ~/.nanobot and the workspace that Nanobot uses to store its files. After this step, Nanobot is ready for provider, model, and channel configuration.

Step 4: Configuring Nanobot

Access your ~/.nanobot/config.json file, then copy and paste the following configuration. Before saving, replace the placeholder values with your own OpenAI API key, model, and WhatsApp number.

"apiKey": "sk-REPLACE_ME"
"model": "openai/[gpt](/glossaire/gpt)-5.3-codex",
"provider": "openai"
"enabled": true,
"allowFrom": ["1234567890"]

Before saving, modify:

• apiKey with your actual OpenAI API key
• model if you wish to use a different model
• allowFrom with your own WhatsApp number

It is important to note that some users have reported inconsistencies with the allowFrom formatting for WhatsApp, suggesting that it works better without the "+" sign depending on their specific setup.

Step 5: Connecting Nanobot to WhatsApp

Before starting the connection process to WhatsApp, ensure that Node.js and npm are installed on your machine, as the WhatsApp bridge operates through a Node-based process.

Start by initiating the connection process in a terminal:

nanobot channels login whatsapp

This will generate a QR code that you need to scan from WhatsApp → Settings → Linked Devices on your phone. Once the device is linked, open a second terminal and start the Nanobot gateway:

This is the process that keeps the channel active so that Nanobot can receive and respond to WhatsApp messages.

Step 6: Testing Your AI Agent on WhatsApp

To test the agent, you will need a second phone. This second phone number must already be added to the allowFrom list in your configuration file. When you send a message to the first phone number connected to Nanobot, it should respond via WhatsApp.

In this example, the prompt asks what is happening in the world. Nanobot then processes the request, performs a web search if the tools are enabled, and returns a detailed overview based on the latest information.

As long as the gateway terminal is running, you can observe the entire workflow of the agent in real-time. This includes receiving the message, calling the tools, generating the response, and sending the reply, making it easy to confirm that everything is working correctly.

Final Thoughts

Setting up Nanobot showed me that building a personal AI agent doesn't have to be overly complicated, although it wasn't entirely frictionless. I appreciated how quickly I could go from a terminal setup to a connected WhatsApp agent that provides useful responses in practice.

However, I encountered a few minor hurdles. On Windows, if Node.js or npm were already installed in a certain configuration, the Python script sometimes failed to detect npm correctly in the terminal, making the initial setup slightly confusing. Additionally, the lack of comprehensive documentation on WhatsApp meant that it wasn't immediately obvious that the interface works by sending messages directly to the connected device rather than through a separate bot chat interface.

Despite these minor issues, Nanobot remains an excellent starting point for anyone looking to build their first AI agent. It provides a basic agent experience without the weight of heavier alternatives. Once the setup is operational, its value becomes immediately apparent, bridging the gap between simple terminal commands and a truly useful personal assistant.