NanoBot

Created on February 2, 2026
Updated on March 23, 2026

Python-based AI assistant with ~4,000 lines of code from Hong Kong University. YAML configuration, simple and clean architecture. Released February 2, 2026.

Ultra-Lightweight Python AI Assistant

NanoBot is an ultra-lightweight personal AI assistant developed by HKUDS (Data Intelligence Lab at the University of Hong Kong), released on February 2, 2026. It delivers core OpenClaw functionality in just ~4,000 lines of Python code — 99% smaller than OpenClaw's 430,000+ lines.

Launch Date: February 2, 2026 Developer: HKUDS (Hong Kong University Data Intelligence Lab) Code Size: ~4,000 lines of Python (99% smaller than OpenClaw) Platforms: Supports 9+ chat platforms (WhatsApp, Telegram, Discord, Feishu, etc.)

Why NanoBot?

Ultra-Lightweight: At ~4,000 lines of Python code, NanoBot is 99% smaller than OpenClaw (430,000+ lines), making it incredibly easy to understand, modify, and deploy.

Clean Architecture: Well-organized, readable Python codebase with skills-based extensibility, agent loop architecture, and cron-based task scheduling.

Multi-Platform Support: Supports 9+ messaging platforms including WhatsApp, Telegram, Discord, Feishu, and more.

Multiple LLM Providers: Works with OpenRouter, Anthropic, OpenAI, DeepSeek, Groq, and Gemini.

Educational Value: Perfect for learning AI agent architecture due to its minimal, focused codebase.

Installation

git clone https://github.com/HKUDS/nanobot
cd nanobot
pip install -r requirements.txt
# Configure config.yaml
python main.py

Quick Start Guide

Get NanoBot up and running quickly.

Step 1: Install

git clone https://github.com/HKUDS/nanobot.git
cd nanobot
npm install
npx nanobot setup

Step 2: Configure

Set your AI model and API key in the configuration.

Step 3: Connect and Go

Link your messaging platform and start using your AI agent.

Full documentation: https://github.com/HKUDS/nanobot#readme

Source code: https://github.com/HKUDS/nanobot

FAQ

Is NanoBot free to use?

Yes, NanoBot is free and open source (MIT license). You only pay for AI model API costs if using external models.

What are the system requirements for NanoBot?

NanoBot requires 512MB RAM of RAM minimum. Runtime: Python 3.8+. It runs on Windows, macOS, and Linux.

Can I self-host NanoBot?

Yes. NanoBot is open source (MIT) and can be self-hosted on your own hardware. Clone the repository from GitHub and follow the installation guide.

How does NanoBot compare to OpenClaw?

NanoBot offers a different approach compared to OpenClaw. While OpenClaw provides the largest ecosystem with 13,729+ skills and maximum flexibility, NanoBot focuses on lightweight. Choose NanoBot if you prioritize its specific features; choose OpenClaw for the broadest compatibility and community support.

Is NanoBot suitable for beginners?

NanoBot requires some technical knowledge to set up (Python 3.8+). If you are a beginner, consider starting with QClaw (one-click install) or MaxClaw (cloud-based, no setup) first, then graduate to NanoBot as you gain experience.

License

MIT License - Free and open source.

Sources

On this page

Ultra-Lightweight Python AI Assistant
Why NanoBot?
Installation
Quick Start Guide
Step 1: Install
Step 2: Configure
Step 3: Connect and Go
FAQ
Is NanoBot free to use?
What are the system requirements for NanoBot?
Can I self-host NanoBot?
How does NanoBot compare to OpenClaw?
Is NanoBot suitable for beginners?
License
Sources