ai-agent

QwenPaw: AI Assistant

Get a personal AI assistant with QwenPaw, deployable on your machine or cloud, ideal.
33,764 stars2,974 forksPythonGuide quality 8/10Updated 8/12/2026100% free · open source
What it does

QwenPaw provides a personal AI assistant that can be deployed on your machine or cloud, supporting multiple chat apps with easily extensible capabilities.

When to use it
  • You need a customizable AI assistant for your startup's specific needs
  • You want to integrate AI capabilities into your existing chat applications
  • You prefer to have control over your AI assistant's deployment, whether on your machine or in the cloud
Ready-to-paste prompt
Ask your QwenPaw assistant to `send a welcome message to new users on our Slack channel` to see it in action
Heads up: Before running QwenPaw, ensure you have Python 3.8 or later installed on your system, as it is a prerequisite for the tool to function correctly
Saves to your device
Use with Claude
New

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

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/qwenpaw && curl -fsSL https://workflowstacks.com/api/skills/qwenpaw/claude-skill -o ~/.claude/skills/qwenpaw/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 QwenPaw: AI Assistant works
Codeflow
Free to inspect

QwenPaw: AI Assistant is a very large Python project (~597k lines across 2468 code files, plus 939 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~597k lines · 2468 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Python · Docker
No API keys detected
Python 58%TypeScript 38%Less 2%Rust 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    pyproject.toml
    Dependencies and the commands it exposes
  3. 3
    src/qwenpaw/__init__.py
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic1288 files
plugins/Sub-packages / plugins895 files
packages/Sub-packages / plugins14 files
docs/Documentation1 files
console/Folder1074 files
website/Project website284 files
scripts/Helper scripts54 files
deploy/Deployment / infrastructure3 files
READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
agentscope-ai
Language
Python
Category
ai-agent
Published
2/24/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.