AI and models · Independent · 21 Oct 2026

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

← AI and models
nanobot: personal AI agent. Self-hosted assistant framework with chat apps and tools.

In simple English

This tool acts as a private helper that connects to artificial intelligence models of your choice. You can talk to it in a web browser, a command-line terminal, or through chat apps like Telegram and Discord. It reads your local files, remembers your preferences across chats, and runs background tasks on a schedule. You need to supply your own model account or run a local model server. It is free to use under an open-source licence.

What it is

A self-hosted personal AI assistant framework written in Python that includes a web user interface, file tools, long-term memory, and multi-agent workflows. It supports model context protocol (a standard way for assistants to connect to external data sources) and exposes an OpenAI-compatible API.

What it is good for

Solo builders who want a private, customizable assistant to summarize documents, automate routine workflows, and answer questions across multiple chat platforms without relying on closed commercial apps.

Stars49k
LicenceMIT
Latestv0.3.5 (2026-09-15)checked 21 Oct 2026
Last code change2026-10-21
Written inPython
Setup effort
3 / 5
Payoff
5 / 5
Good
  • Runs locally or on your own server, keeping your data under your control.
  • Connects to multiple chat platforms including Telegram, Discord, Slack, and email.
  • Includes a built-in web user interface for managing chats, files, and scheduled tasks.
Watch for
  • Requires Python 3.11 or newer and some command-line setup experience.
  • Does not include an AI model account, so you must pay a provider or run your own hardware.
  • Running background gateways and scheduled tasks requires keeping the server awake.
Replaces

Closed commercial AI chat apps and manual script scheduling

Works well with

Ollama

Similar repositories
  • LibreChat-AI/LibreChat46k stars

    Another self-hosted chat interface for multiple language models, though less focused on autonomous agents and file workflows.

  • Significant-Gravitas/AutoGPT188k stars

    An autonomous agent framework that runs multi-step tasks, but with a heavier focus on agent loops rather than chat app integration.

Also reviewed on Repo Radar
  • ggml-org/llama.cpp132k stars

    A C and C++ library and command-line tool for running language models locally.

  • EleutherAI/lm-evaluation-harness14k stars

    Runs standard question sets against a language model and reports the scores.

  • mudler/LocalAI50k stars

    Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

Install
curl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh
nanobot webui

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: AI & Automation › AI Assistants & Agents › Autonomous Agents.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.