🔥
HotRepo
QwenPaw — Self-host Your Personal AI Assistant; easy to install, deploy on your own machine or on th
📦
agentscope-ai

QwenPaw — Self-host Your Personal AI Assistant; easy to install, deploy on your own machine or on th

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

⭐ 37.1k🍴 3.2kTypeScript📜 apache-2.0🐳 Docker Compose#agent#agent-harness#agentscope#ai-agent

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.

⭐ 35,803 stars on GitHub · 🍴 3,188 forks · 📜 License: apache-2.0 · 💻 Language: TypeScript

What is QwenPaw?

This is a powerful opensource communication platform — self-host it to keep full control over your team's chat data.

Main components

  • Sandbox — Kernel-level execution isolation using Seatbelt (macOS), Bubblewrap / Landlock (Linux), and AppContainer (Windows). Shell commands run inside a restricted filesystem view.
  • Tool Guard — YAML rule engine with ShellEvasionGuardian inspects every tool call before execution, detecting command injection, path traversal, reverse shells, and obfuscated attacks. Configurable ...
  • File Guard — Independent of Tool Guard; blocks agent access to sensitive files and directories (default-protects ~/.qwenpaw.secret/, ~/.ssh, etc.).
  • Skill Scanner — Pre-activation scanning with block / warn / off modes and whitelist support. Detects prompt injection, hardcoded secrets, data exfiltration, and more.
  • Access Policy — Declarative access rules that allow, deny, or request human approval for each capability call, with tool-level granularity and source-aware matching.

The biggest strength is full control over chat data — something no commercial alternative grants you.

Best for remote teams, tech companies, communities — anyone who wants chat history kept private.

Topics: the project is tagged with popular topics:

  • 🏷️ agent
  • 🏷️ agent-harness
  • 🏷️ agentscope
  • 🏷️ ai-agent
  • 🏷️ ai-agents
  • 🏷️ chatbot
  • 🏷️ harness-engineering
  • 🏷️ llm-tools
  • 🏷️ llms
  • 🏷️ loop-engineering

📸 Screenshots

QwenPaw TUI

agentscope-ai%2FQwenPaw | Trendshift

Discord

DingTalk

RedNote

Quick install

The project supports Docker Compose:

git clone https://github.com/agentscope-ai/QwenPaw.git
cd QwenPaw
docker compose up -d

Check the README in the repo for required env variables.

Minimum system requirements

Component Recommended
RAM 2048 MB
CPU 2 vCPU
Disk 25 GB SSD
OS Ubuntu 22.04 LTS / Debian 12
Docker 24.0+

⚡ Deploy fast on VSIS

Use the VSIS VPS Lite 2GB RAM / 2 vCPU / 25GB SSD (~104k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running QwenPaw smoothly.

🎯 Benefits:

  • One-command docker compose up -d deploy in 2 minutes
  • Dedicated IPv4, root access, unmetered domestic bandwidth
  • Daily snapshot backup
  • Free install assistance from the VSIS team

👉 See matching VPS plans at vsis.net

Resources


Article compiled from GitHub data on 17/10/2026. Star/fork counts may have changed — see live numbers via the GitHub link.