QwenPaw
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
What is QwenPaw?
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
Overview of QwenPaw
What it is
QwenPaw is a personal AI assistant that can be deployed locally or in the cloud. It supports multiple chat applications and is designed to be extensible through skills and plugins. The project is open source under the Apache-2.0 license and is built by the AgentScope team.
Key features
- Three-layer memory: live working context, full verbatim history, and a self-evolving personal knowledge base (ReMe).
- Supports local models (QwenPaw-Flash 2B/4B/9B/35B-A3B/27B) and works with Ollama, LM Studio, or 14+ cloud providers.
- Security features include kernel-level Sandbox, Tool Guard, File Guard, Skill Scanner, and Access Policy.
- Multi-agent and parallel execution with independent agents, sub-agents, and Agent Communication Protocol (ACP).
- Unified file workspace for navigation, preview, editing, diffs, upload, and download.
- Extensible via Skills, Plugin architecture with a marketplace, and MCP integration.
- Reachable through DingTalk, Lark, WeChat, Discord, Telegram, iMessage, QQ, Console, TUI, and desktop app.
- Deploy locally to keep data on your machine with no third-party hosting.
Use cases
- Automation and scheduling: recurring tasks like news digests, report generation, multi-channel broadcasting.
- Code and development: read, edit, review, and test code in projects.
- Document processing: read, write, and convert PDF, Word, Excel, and PowerPoint files.
- Information gathering: web search, subscriptions, video summarization, personal knowledge base queries.
- Multi-channel operations: push alerts, summaries, or AI-generated content to multiple platforms simultaneously or per channel.
- Custom workflows: combine built-in capabilities, plugins, and scheduled tasks.
Getting started
Option 1: Pip Install (requires Python >= 3.11, < 3.14) bash pip install qwenpaw qwenpaw init --defaults qwenpaw app Option 2: Script Install (no Python setup required) macOS / Linux: bash curl -fsSL https://qwenpaw.agentscope.io/install.sh | bash Windows (CMD): CMD curl -fsSL https://qwenpaw.agentscope.io/install.bat -o install.bat && install.bat Windows (PowerShell): powershell irm https://qwenpaw.agentscope.io/install.ps1 | iex
License and pricing
The project is licensed under Apache-2.0 and is open source.
Based on the project's public README and repository metadata.