Nanobot

Open Source

3.9 / 5

Last updated: Jun 10, 2026

About

Nanobot is an open-source, ultra-lightweight agent runtime created by the HKU Data Science (HKUDS) team. It's designed for people who want to own their AI agent stack, providing a small, readable core plus practical pieces for real long-running agents: WebUI, chat channels, tools, memory, MCP, model routing, and deployment.

Key Features

Persistent Workflows — goals, memory, tools, and chat context survive long-running work
Chat-Native Reach — WebUI, API, Telegram, Feishu, Slack, Discord, Teams, email
Model Freedom — OpenAI-compatible APIs, local LLMs, image generation, search, fallbacks
MCP Protocol — complete MCP integration with custom extensions
Memory System — token-based memory management with Dream two-stage memory
Multi-Channel — WeChat, QQ, Feishu, DingTalk, Discord, Slack, Telegram
Skills System — built-in skills and ClawHub skill marketplace integration

Use Cases

Personal AI Assistant, Team Collaboration, Workflow Automation, Multi-Channel AI Customer Service, Local Development Assistant

Pros & Cons

Pros

Ultra-Lightweight — clean core, easy to understand and customize
Rapid Updates — near-daily releases, fast feature iteration
Broad Model Support — supports virtually all major LLM providers and local models
Multi-Channel Coverage — full coverage of global mainstream IM platforms
Active Community — rapidly growing developer and user community

Cons

Fast Iteration Pace — frequent updates may cause compatibility issues
Scattered Documentation — some features lack centralized documentation
Early Stage — project started in February 2026, some features still maturing

Reviews

No reviews yet

Be the first to share your experience with this agent.

Write a Review

Pricing

Open Source / Free (MIT License)