workflowstacks
automation

nanobot: Deploy Self‑Hosted AI Agents for Faster Automation

Launch a lightweight Python AI agent framework with WebUI, memory, and multi‑agent workflows—ideal for founders building custom chatops or automation tools. 49k+ GitHub stars.
48,931 stars+170★ this week8,617 forksPythonGuide quality 8/10 · reviewed Sep 29Updated 10/10/2026100% 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.

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
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
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/nanobot && curl -fsSL https://workflowstacks.com/api/skills/nanobot/claude-skill -o ~/.claude/skills/nanobot/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How nanobot: Deploy Self‑Hosted AI Agents for Faster Automation works
Codeflow
Free to inspect

Nanobot: Deploy Self‑Hosted AI Agents for Faster Automation 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
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    nanobot/__main__.py
    Where the program starts running
  4. 4
    pyproject.toml
    Dependencies and the commands it exposes
  5. 5
    nanobot/__init__.py
    Inside nanobot/ — the main logic begins here
What's in each folder
nanobot/Core code — the actual logic589 files
docs/Documentation53 files
webui/Folder271 files
tui/Folder48 files
scripts/Helper scripts3 files
tests/Tests — proof it works308 files
images/Images & static assets7 files
.github/CI / automation (GitHub Actions)5 files
READMEHas testsDocumentedCI checksDocker readyMIT licenseUpdated this month
Quick Actions
Details
Creator
HKUDS
Language
Python
Category
automation
Published
2/1/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/nanobot.svg)](https://workflowstacks.com/skills/nanobot?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Free n8n template

AI Support Agent (Chat)

A chat agent that answers customer questions from YOUR business info — with conversation memory. It never invents policies; anything it doesn't know, it hands to a human.

Outcome guide

Score your leads by ideal-customer fit

You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Related skills

More automation tools founders pair with this one.

automation★ 206,888
n8n: Scale Your Startup with 207k+ GitHub-Star Automation
n8n lets founders automate workflows across 400+ services, blending visual no‑code design with custom TypeScript code—self‑hosted or cloud.
automation★ 155,483
Langflow: Rapidly Build AI Agents & Workflows
Create and launch AI‑powered agents and multi‑step workflows without deep ML code—ideal for founders scaling generative‑AI products. 155k+ GitHub stars
automation★ 129,414
MoneyPrinterTurbo: AI Video Automation
Generate short videos with one click using AI. For founders needing automation.
automation★ 62
keenetic-zapret2-manager
Advanced Zapret2 manager for Keenetic routers (OpenWrt/Entware). Bypass DPI restrictions (Discord, Roblox, Kick, Wattpad, Mullvad and more) with smart DPI profiles, IPSET client filtering, IPv6 support, Telegram alerts, HealthMon watchdog, blockcheck automation and Web UI. | Keenetic icin gelismis Zapret2 yonetim araci.
automation★ 6,233
loopx
A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.
automation★ 683
Boost productivity with pi-extensions
Get native Chrome DevTools extensions for automation and web scraping, ideal for startup founders and developers using Node.js and TypeScript.