automation

nanobot: Automate Workflows

Name: nanobot: Automate Workflows
Author: HKUDS

Get a self-hosted personal AI agent framework with nanobot. For founders seeking automation and workflow efficiency with 47k+ GitHub stars.

47,405 stars8,368 forksPythonHealth Score 9/10Updated 8/26/2026100% free · open source

What it does

Nanobot is a lightweight, self-hosted personal AI agent framework that allows you to automate tasks, workflows, and interactions using a Python-based framework with a WebUI and multi-agent capabilities.

Install / run

git clone https://github.com/HKUDS/nanobot.git && cd nanobot && pip install -r requirements.txt

When to use it

•When you need to automate repetitive tasks and workflows across multiple applications and services
•When you want to build custom AI-powered chat apps and agents for customer support or personal use
•When you require a self-hosted solution for data privacy and security reasons, with full control over your AI agents and data

Quick start

1Run `python app.py` to start the Nanobot server and access the WebUI at http://localhost:5000
2Create a new agent by clicking on the 'Agents' tab and following the agent creation wizard, or by editing the `agents.json` file
3Configure the agent's memory and MCP (Master Control Program) settings by editing the `config.json` file
4Integrate Nanobot with external services and APIs by using the built-in `api` module and creating custom API connectors
5Use the `workflow` module to define and execute multi-agent workflows and automate complex tasks

Ready-to-paste prompt

python app.py --agent myagent --task 'Send a message to my chat app saying "Hello, world!"'

Heads up: Make sure you have Python 3.8 or later installed, as Nanobot is not compatible with earlier versions of Python, and also ensure you have the required dependencies installed by running `pip install -r requirements.txt` before starting the server

Saves to your device

Topics

agent-framework

ai-agent

ai-agents

chatbot

chatops

discord-bot

llm-agents

llms

local-llm

mcp

model-context-protocol

multi-agent

openai-compatible

openclaw

personal-ai-assistant

python

self-hosted

telegram-bot-ai-assistant

webui

workflow-automation

How nanobot: Automate Workflows works

Codeflow

Free to inspect

Nanobot: Automate Workflows is a very large Python project (~168k lines across 549 code files, plus 445 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size

Very large codebase

~168k lines · 549 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python · Docker

No API keys detected

Python 72%TypeScript 27%

Where to start reading