Who it is forSomeone who wants a personal assistant that remembers context but does not want their history on a third party server.
The problemHosted assistants keep your conversations on their servers and forget context between sessions.
The outcomeA local Qwen Paw console with working memory, history and a personal knowledge base on your machine.
What you need first
- Python 3.11 or newer for the pip install, or Docker
- A model: QwenPaw Local with QwenPaw-Flash models, Ollama on the host, or a provider API key
- Accounts for any chat channels you want to connect (Discord, Telegram and others)
Steps
- Install Qwen Paw with the installer script or pip (Python 3.11 or newer)
- Open a new terminal and run
qwenpaw init --defaults - Start the app with
qwenpaw appand open the console - Pick a local QwenPaw-Flash model or add a provider key, then start chatting
- To remove it later,
qwenpaw uninstallkeeps config and data
Prompt for your agent
Install agentscope-ai/QwenPaw on this computer, run qwenpaw init --defaults and qwenpaw app, set it up with <local model or provider>, and confirm the console works before I connect any channels.
Caveat.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for agentscope-ai/QwenPaw and "Run a private AI assistant with memory on your own machine"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer