Audience
Developers and AI researchers requiring an AI agent framework to build, customize, and experiment with autonomous assistants
About nanobot
nanobot is an open source, ultra-lightweight personal AI assistant framework designed to deliver the core agent loop and autonomous AI capabilities in a minimal, readable codebase, approximately ~3,400–4,000 lines of Python, which is ~99% smaller than comparable large agent frameworks. It’s intentionally simple and modular, making it easy to understand, extend, and experiment with for research or custom projects. nanobot supports persistent memory, scheduled tasks, built-in tools, and integration with multiple large language models (via OpenRouter or other providers), and can run locally or be deployed quickly with CLI commands; it also offers optional real-time web search and multi-platform chat interfaces (e.g., Telegram, Discord, WhatsApp, Feishu) so you can interact with the agent from different environments. Its minimal footprint enables fast startup, low resource use, and a clean architecture that developers can adapt without heavy abstractions.