QwenPaw

What is QwenPaw?

QwenPaw is a personal AI assistant from the AgentScope team that you install on your own machine or server rather than use as a hosted service. After setup you reach the same agent through a web console, a terminal interface, a desktop app in beta, or chat channels including DingTalk, Lark, WeChat, Discord, Telegram, iMessage and QQ. It keeps a three-layer memory made of working context, full conversation history and a personal knowledge base stored as Markdown, and it can spawn separate agents with their own memory and skills. Skills cover scheduling, documents, browsing and news, and plugins and MCP connect outside tools. Security checks include a sandbox, tool and file guards and a skill scanner that block dangerous commands before they run. It can use cloud providers such as DashScope, OpenAI, Anthropic and Gemini, or run local models through its built-in runtime, Ollama or LM Studio without an API key. The project lists no subscription price; model providers you choose may bill separately.

Use cases

• Schedule recurring reports and news digests
• Chat with one assistant across several messaging apps
• Read, edit and test code in a project
• Convert PDF, Word, Excel and PowerPoint files
• Run a private assistant with local models
• Run several agents with separate memory
• Broadcast alerts to multiple channels

Who it's for

• Developers
• Self-hosting enthusiasts
• Teams using DingTalk or Lark
• AI agent builders

Why use QwenPaw

• Running locally keeps your data on your machine, with no third-party hosting or data upload.
• Local models through the built-in runtime, Ollama or LM Studio remove the need for an API key and per-call fees.
• One agent answers in the console, terminal and your messaging apps, with the same memory and skills everywhere.
• Built-in guards block dangerous commands before they run, which matters for an agent that touches files and shells.
• Skills, plugins and MCP let you extend it for scheduled digests, document work and coding without writing a new app.

QwenPaw features

• Three-layer memory with a Markdown knowledge base
• Built-in local runtime plus Ollama and LM Studio support
• 14+ cloud model providers
• Sandbox, Tool Guard, File Guard and Skill Scanner
• Independent agents and runtime sub-agents
• Agent Communication Protocol for cross-system orchestration
• Skills for scheduling, documents, browser and news
• Plugin architecture with a marketplace and MCP integration
• Unified file workspace with preview, diffs and upload
• Console, terminal UI and desktop app
• Cron-based scheduled tasks

QwenPaw integrations

• DingTalk
• Lark
• WeChat
• Discord
• Telegram
• iMessage
• QQ
• Ollama
• LM Studio
• DashScope
• OpenAI
• Anthropic
• Google Gemini
• DeepSeek
• OpenRouter
• ModelScope

How to get started with QwenPaw

1. Install with pip, the one-line installer, Docker or the desktop app, then run qwenpaw init.
2. Start it with qwenpaw app and open the console at 127.0.0.1:8088, or run qwenpaw for the terminal chat.
3. In Settings, choose a model: a local model, or a cloud provider with its API key.
4. Add skills, connect channels such as Telegram or Discord, and set up cron schedules for recurring tasks.
5. Create extra agents with their own memory and skills when you want separate assistants for different work.

QwenPaw limitations

• The desktop application is in beta, with incomplete compatibility testing
• Cloud model providers need an API key before the assistant works
• The macOS desktop build is not notarized, so Gatekeeper asks you to confirm opening it
• Pip installation requires Python 3.11 or newer

QwenPaw pricing

QwenPaw is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

QwenPaw alternatives

The main QwenPaw alternatives listed on Debuly are OpenClaw, Open WebUI, Hermes Agent, AnythingLLM, LibreChat and Dify. The table compares pricing and platforms; order is A–Z.

1. 

   AnythingLLM

   Open-source AI app for chatting with your documents and running agents, on desktop, in Docker or as a hosted team workspace.

   Chat assistantsAutomation and agentsDeveloper platforms
   Open sourceVisit AnythingLLM (official site)
2. 

   Dify

   Platform for building LLM apps, agents and RAG workflows on Dify Cloud or your own infrastructure, with a free Sandbox tier.

   Developer platformsAutomation and agentsChat assistants
   FreemiumVisit Dify (official site)
3. 

   Hermes Agent

   Free, MIT-licensed AI agent from Nous Research with persistent memory, auto-built skills, scheduling and chat-app access.

   Automation and agentsCodingProductivity
   Open sourceVisit Hermes Agent (official site)
4. 

   LibreChat

   Free open-source AI chat platform that puts many model providers, agents, code execution and MCP tools in one self-hostable app.

   Chat assistantsDeveloper platformsAutomation and agents
   Open sourceVisit LibreChat (official site)
5. 

   Open WebUI

   Self-hosted AI chat platform for Ollama and OpenAI-compatible models with RAG, agents, tools, notes, channels and role-based access.

   Chat assistantsDeveloper platformsAutomation and agents
   Open sourceVisit Open WebUI (official site)
6. 

   OpenClaw

   Open-source personal AI assistant that runs on your own devices and takes actions for you through WhatsApp, Telegram, Slack, Discord and other chat apps.

   Automation and agentsChat assistantsProductivity
   Open sourceVisit OpenClaw (official site)

QwenPaw FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from avatars.githubusercontent.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.