HKUDS/nanobot

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

What it solves

nanobot is a self-hosted personal AI agent framework that allows users to create a persistent, customizable AI assistant. It solves the problem of fragmented AI interactions by providing a single gateway that connects multiple LLM providers, long-term memory, and various communication channels (like Telegram, Discord, and Slack) into one unified, lightweight runtime.

How it works

The project centers around a small agent loop where messages from various channels are processed by an LLM. The LLM determines when to use tools or pull in memory and skills as context. It avoids heavy orchestration layers to remain lightweight and readable. It supports model routing, multi-agent delegation, and MCP (Model Context Protocol) integrations to extend its capabilities.

Who it’s for

It is designed for individuals who want to own their AI stack, self-host their agents, and integrate them into their daily workflows across different chat apps and terminals without relying on a giant platform.

Highlights

  • Multi-channel reach: Connects to WebUI, terminal, Telegram, Discord, Slack, WeChat, Email, Mattermost, and Linear.
  • Persistent Memory: Features long-term memory through "Dream" and session history that survives long-running work.
  • Extensible Tooling: Supports MCP servers, shell access, web search, image generation, and scheduled automations via a calendar system.
  • Model Agnostic: Compatible with OpenAI-compatible APIs, local LLMs (via Ollama or vLLM), and supports fallback models.
  • Flexible Interface: Includes a bundled WebUI for managing topics and workspaces, and a native TUI for terminal-based interaction.

Related

  • Dispatch
    nanoMuse: An Open-Source Cross-Device AI Agent

    nanoMuse is an open-source personal AI agent that operates across Android, iOS, Windows, macOS, and Linux, using device screens as "hands" to perform tasks in apps without APIs.

  • Project
    RTGS2017/NagaAgent

    NagaAgent is a cross‑platform desktop AI assistant (Windows/macOS/Linux) that offers chat with any OpenAI‑compatible LLM, custom tool‑calling via JSON blocks, graph‑RAG memory stored in Neo4j, a Live2D animated avatar, voice synthesis/recognition with lip‑sync, a plug‑in MCP framework for weather, web search, game guides, etc., and community features like a forum and skill marketplace. It ships as an Electron/Vue front‑end plus Python FastAPI back‑end, is installable via `uv sync` (or pip), and is dual‑licensed (AGPL‑3.0 + proprietary).

  • Project
    siddsachar/row-bot

    Row‑Bot is a self‑hosted desktop AI assistant that lets you converse with LLMs to create files, run code, manage designs, and interact with services—all while keeping data locally. It offers memory via a personal knowledge graph, goal‑driven agents, approval‑gated actions, multi‑device remote access, and integrations (GitHub, Notion, Slack, etc.). Runs on Windows/macOS/Linux or Docker, using Ollama or any OpenAI‑compatible provider, and stores everything securely on your machine.

  • Project
    zhayujie/CowAgent

    CowAgent is an open‑source, self‑hosted AI assistant that plans tasks, runs tools, keeps a personal knowledge base, and can operate as a team of cooperating agents. It supports many LLM providers, multimodal input, dozens of chat channels (Telegram, Slack, WeChat, etc.), a plug‑in skill system, and a three‑tier memory with nightly “Deep Dream” distillation. Install via a one‑line script or Docker, manage everything through a web console, and extend the system through the public Skill Hub or custom tool integrations.

  • Project
    clawdotnet/openclaw.net

    OpenClaw.NET is a .NET‑native, self‑hosted AI‑agent runtime with a desktop Avalonia UI (AgentQi Companion). It runs a gateway that talks to any OpenAI‑compatible model, offers streaming, tool execution, session memory, and many integrations (REST, WebSocket, MCP, 80+ tools, channel adapters). The gateway can be compiled with NativeAOT, making it suitable for edge or on‑prem deployments. Users can start via a ready‑made desktop bundle or from source, configure the assistant through chat commands, and extend functionality with .NET plugins or reusable MetaSkill DAG workflows.