QwenPaw

Autonomous Agents 💻 Python ⚖️ Apache-2.0 🟢 Actively maintained
34.9k stars

QwenPaw is a personal AI assistant platform that can be deployed locally or in the cloud, featuring a three-layer memory system, multi-agent support, and integration with various messaging channels. It solves the problem of managing personal tasks, information, and communications through an extensible, secure assistant. It is for developers and users who want a customizable, self-hosted AI assistant.

QwenPaw demo
🎞️ Demo from the project README

✨ Key features

  • Three-layer memory with self-evolving knowledge base
  • Local or cloud deployment with no API key required
  • Kernel-level security with sandbox and guards
  • Multi-agent and parallel execution with ACP
  • Unified file workspace for editing and preview
  • Extensible with skills, plugins, and MCP integration

🎯 Use cases

  • Automate recurring tasks like news digests and reports
  • Assist with code reading, editing, and testing
  • Process documents including PDF, Word, Excel, and PowerPoint
  • Gather information from web and personal knowledge base
  • Broadcast messages across multiple channels like DingTalk and Discord

📦 Installation

🧰 Requirements: Python >= 3.11, < 3.14 for pip install; or use script install or Docker; optional API keys for cloud providers.

Option 1: Pip Install

pip install qwenpaw
qwenpaw init --defaults
qwenpaw app

Option 2: Script Install

macOS / Linux:

curl -fsSL https://qwenpaw.agentscope.io/install.sh | bash

Windows (CMD):

curl -fsSL https://qwenpaw.agentscope.io/install.bat -o install.bat && install.bat

Windows (PowerShell):

irm https://qwenpaw.agentscope.io/install.ps1 | iex

After install, run:

qwenpaw init --defaults
qwenpaw app

Option 3: Docker

docker pull agentscope/qwenpaw:latest
docker run -p 127.0.0.1:8088:8088 \
  -v qwenpaw-data:/app/working \
  -v qwenpaw-secrets:/app/working.secret \
  -v qwenpaw-backups:/app/working.backups \
  agentscope/qwenpaw:latest

🚀 Usage

After installation, run:

qwenpaw init --defaults
qwenpaw app

Then open the Console in your browser at http://127.0.0.1:8088/ to configure your model.

⚠️ Good to know

The desktop application is in beta; script install may not work in restricted network environments; Windows LTSC users may need manual configuration.

❓ FAQ

What are the system requirements for QwenPaw?

For pip install, Python >= 3.11 and < 3.14 is required. Script install and Docker options do not require manual Python setup.

Can I use QwenPaw without an API key?

Yes, the built-in QwenPaw Local runtime works without an API key, and it also supports local models via Ollama or LM Studio.

How do I connect QwenPaw to messaging channels?

After starting the app, you can configure channels like DingTalk, Lark, WeChat, etc., through the Console or documentation.

Is my data secure with QwenPaw?

QwenPaw includes kernel-level security features like sandboxing and guards, and you can deploy locally to keep data on your machine.

📊 Repository

Stars★ 34,934
Forks🍴 3,061
Open issues🐛 935
Last commit🕒 Sep 4, 2026
Created📅 Feb 2026
Language💻 Python
License⚖️ Apache-2.0

🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.