Verified project record

HKUDS/nanobot

A lightweight, self-hostable personal AI agent runtime that bundles a browser workbench, chat integrations, tools, memory, and automation in a readable core. It supports local or server-side gateway deployment, requires Python 3.11 or newer, and requires an OpenAI-compatible LLM provider or local LLM server to function.

Project overview

Offers an ultra-lightweight agent core with a bundled WebUI that requires no extra build step when installing the published wheel, alongside model routing that supports local LLM servers and external providers.

Project type: MCP · AI Agent · Workflow
Use cases: Knowledge Q&A · Automation
Deployment: Refer to project documentation
License: MIT

Best for

Developers and AI engineers who want a self-hosted agent runtime to orchestrate long-running automations across multiple chat platforms.
General users who prefer a guided setup wizard and a bundled WebUI for managing local or server-side agent interactions without extra build steps.

Key capabilities

Ships a browser workbench for chat sessions, workspace controls, Apps, Skills, Automations, and settings inside the published wheel.
Connects to chat apps such as Telegram, Discord, Slack, WeChat, Email, Mattermost, and others to run agent interactions.
Provides files, shell, web search, web fetch, MCP, cron, image generation, and subagents for agent tasks.
Keeps session history and long-term memory through Dream to preserve context.
Runs long-horizon goals and scheduled automations.
Exposes an OpenAI-compatible API for integrations.
Exposes a Python SDK for integrations and runtime controls.
Supports local LLMs, image generation, search, and model fallbacks.

Limitations and risks

The runtime requires Python 3.11 or newer.
Building from source requires additional npm/bun steps which might fail on Windows.
Operation requires an OpenAI-compatible LLM provider or a local LLM server, meaning inference may rely on external services unless a local model server is configured.

Getting started

The documented setup difficulty is rated easy because a one-command installer is available via curl/PowerShell and a guided wizard is provided for non-technical users. The first success path involves running the installer, executing the onboard wizard, configuring an API key, and starting the WebUI.

Evidence and sources

GitHub project description: Lightweight, open-source AI agent for your tools, chats, and workflows.
README: Install nanobot with no terminal/config background
README: nanobot is a self-hosted personal AI agent runtime. It can: - run in a browser WebUI or terminal - connect to Telegram, Discord, Slack, WeChat, Email, Mattermost, and other chat a…
README: v0.2.2 - Durability Release Highlights: - Segmented WebUI transcripts - Python SDK runtime controls - Automation management - Search/STT provider improvements - Gateway/session/pr…
README: 2026-07-10 Stable model routing, multiline CLI input, new automation guide.

Reviewed at: 2026-07-17T07:26:45Z

Open original GitHub project