Picture by Writer
# Introduction
I used to be on the lookout for a substitute for OpenClaw, not as a result of it isn’t helpful, however as a result of it could actually really feel too heavy and bloated for easy on a regular basis use. I needed one thing light-weight, simple to arrange, and easy to connect with WhatsApp with out going by way of too many difficult steps. That’s after I got here throughout Nanobot on GitHub, and I additionally seen that many individuals had been beginning to speak about it on YouTube.
On this tutorial, we are going to discover the Nanobot structure and the way it works. Then, in six easy steps, we are going to undergo the set up, setup, and strategy of connecting it to WhatsApp so you can begin utilizing it as a 24/7 synthetic intelligence (AI) agent for a variety of duties.
# Utilizing Nanobot For Your First AI Agent
Nanobot is a superb selection for a primary AI agent as a result of it retains the general setup easy whereas nonetheless supporting the options that matter in real-world utilization. It could actually connect with messaging platforms akin to WhatsApp, Telegram, Slack, Discord, Feishu, QQ, and electronic mail, whereas additionally working with a variety of mannequin suppliers and mannequin context protocol (MCP) software servers. This gives inexperienced persons with a transparent strategy to perceive how an agent is structured with out beginning with a system that feels overly advanced.
Structure of Nanobot | Picture from HKUDS/nanobot
It additionally stands out as a substitute for OpenClaw as a result of it provides sensible integrations and on a regular basis usability from the beginning. Alongside messaging channels, it helps software calling, internet search, scheduled duties, voice transcription, real-time progress streaming, and a number of supplier choices, which makes it simpler to show it right into a helpful private assistant as a substitute of only a demo undertaking.
# Step 1: Putting in uv
First, set up uv, which Nanobot makes use of to handle the Python atmosphere and dependencies. Then, affirm it was put in appropriately by checking the model.
curl -LsSf https://astral.sh/uv/set up.sh | sh
Verify the set up:
Output:
uv 0.10.9 (f675560f3 2026-03-06)
# Step 2: Putting in Nanobot
As soon as uv is put in, use it to put in the Nanobot package deal. It will add the Nanobot command line interface (CLI) so it may be launched instantly from the terminal.
uv software set up nanobot-ai
# Step 3: Initializing Your Nanobot Undertaking
Subsequent, run the onboarding command to initialize Nanobot.
This creates the fundamental native setup, together with the default configuration listing at ~/.nanobot and the workspace Nanobot makes use of to retailer its information. After this step, Nanobot is prepared for supplier, mannequin, and channel configuration.
# Step 4: Including Your Nanobot Configuration
Navigate to your ~/.nanobot/config.json file, then copy and paste the configuration beneath. Earlier than saving, change the placeholder values with your personal OpenAI API key, mannequin, and WhatsApp quantity.
{
"suppliers": {
"openai": {
"apiKey": "sk-REPLACE_ME"
}
},
"brokers": {
"defaults": {
"mannequin": "openai/gpt-5.3-codex",
"supplier": "openai"
}
},
"channels": {
"whatsapp": {
"enabled": true,
"allowFrom": ["1234567890"]
}
}
}
Earlier than you save, edit:
apiKeytogether with your actual OpenAI API keymannequinif you wish to use a unique mannequinallowFromwith your personal WhatsApp quantity
One necessary be aware — current Nanobot points present that WhatsApp allowFrom formatting might be barely inconsistent in apply, and a few customers report it really works higher with out the “+” signal relying on their particular setup.
# Step 5: Connecting Nanobot To WhatsApp
Earlier than beginning the WhatsApp login move, make sure that Node.js and npm are put in in your machine, for the reason that WhatsApp bridge runs by way of a Node-based course of.
First, begin the login move in a single terminal:
nanobot channels login whatsapp
It will generate a QR code that it is advisable scan from WhatsApp → Settings → Linked Gadgets in your cellphone. As soon as the machine is linked, open a second terminal and begin the Nanobot gateway:
That is the method that retains the channel operating so Nanobot can obtain and reply to WhatsApp messages.
# Step 6: Testing Your AI Agent On WhatsApp
To check the agent, you’ll need a second cellphone. This second cellphone quantity ought to already be added to the allowFrom checklist in your configuration file. Once you ship a message to the primary cellphone quantity related to Nanobot, it ought to reply by way of WhatsApp.
On this instance, the immediate asks what is going on on the earth. Nanobot then processes the request, performs an online search if instruments are enabled, and returns an in depth snapshot based mostly on the most recent data.
Whereas the gateway terminal is operating, you’ll be able to observe the complete agent workflow in actual time. This contains receiving the message, calling instruments, producing the response, and sending the reply again, which makes it simpler to substantiate that every thing is functioning appropriately.
# Last Ideas
Establishing Nanobot confirmed me that constructing a private AI agent doesn’t must be overly difficult, although it was not totally friction-free. I appreciated how shortly I may transition from a terminal setup to a working WhatsApp-connected agent that gives helpful responses in apply.
Nevertheless, I did encounter just a few minor hurdles. On Home windows, if Node.js or npm was already put in in a sure configuration, the Python script typically didn’t detect npm appropriately within the terminal, which made the preliminary setup barely complicated. Moreover, the dearth of intensive WhatsApp documentation meant it was not instantly apparent that the interface works by messaging the related machine instantly somewhat than by way of a separate bot chat interface.
Regardless of these minor points, Nanobot stays a robust start line for anybody trying to construct their first AI agent. It gives a core agent expertise with out the overhead of heavier alternate options. As soon as the setup is operational, its worth turns into instantly obvious, bridging the hole between easy terminal instructions and a really useful private assistant.
Abid Ali Awan (@1abidaliawan) is an authorized information scientist skilled who loves constructing machine studying fashions. Presently, he’s specializing in content material creation and writing technical blogs on machine studying and information science applied sciences. Abid holds a Grasp’s diploma in expertise administration and a bachelor’s diploma in telecommunication engineering. His imaginative and prescient is to construct an AI product utilizing a graph neural community for college students battling psychological sickness.
