# AI use cases for Qwen Paw (agentscope-ai/QwenPaw) Repo: [agentscope-ai/QwenPaw](https://github.com/agentscope-ai/QwenPaw) | Use cases: 3 | Page: https://dedupedai.com/use-cases/agentscope-ai-qwenpaw/ QwenPaw is a personal AI assistant you deploy locally or in the cloud and reach from many chat channels, including Discord, Telegram, iMessage, DingTalk, Lark and WeChat. It has three-layer memory, a file workspace, skills and plugins, MCP integration and built-in security guards. It can run on its own QwenPaw-Flash local models with no API key. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run a private AI assistant with memory on your own machine: https://dedupedai.com/use-cases/agentscope-ai-qwenpaw/run-a-private-ai-assistant-on-your-own-machine/ - Deploy Qwen Paw in Docker with data, secrets and backups kept: https://dedupedai.com/use-cases/agentscope-ai-qwenpaw/deploy-qwenpaw-in-docker-with-persistent-volumes/ - Schedule a daily news digest sent to Telegram or Discord: https://dedupedai.com/use-cases/agentscope-ai-qwenpaw/schedule-a-daily-news-digest-to-telegram-or-discord/ ## How to run a private AI assistant with memory on your own machine with Qwen Paw Repo: [agentscope-ai/QwenPaw](https://github.com/agentscope-ai/QwenPaw) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README Install Qwen Paw, initialise it with defaults and open the console so your data stays local. **Who it is for:** Someone who wants a personal assistant that remembers context but does not want their history on a third party server. **The problem:** Hosted assistants keep your conversations on their servers and forget context between sessions. **The outcome:** A local Qwen Paw console with working memory, history and a personal knowledge base on your machine. ### Steps 1. Install Qwen Paw with the installer script or pip (Python 3.11 or newer) 2. Open a new terminal and run `qwenpaw init --defaults` 3. Start the app with `qwenpaw app` and open the console 4. Pick a local QwenPaw-Flash model or add a provider key, then start chatting 5. To remove it later, `qwenpaw uninstall` keeps config and data ### Prompt to paste into your agent ```text Install agentscope-ai/QwenPaw on this computer, run qwenpaw init --defaults and qwenpaw app, set it up with , and confirm the console works before I connect any channels. ``` ### Caveat Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/agentscope-ai-qwenpaw/run-a-private-ai-assistant-on-your-own-machine/ ## How to deploy Qwen Paw in Docker with data, secrets and backups kept with Qwen Paw Repo: [agentscope-ai/QwenPaw](https://github.com/agentscope-ai/QwenPaw) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Run the official Docker image with separate volumes for data, secrets and backups. **Who it is for:** A home server owner who wants the assistant always on and easy to upgrade. **The problem:** Running an assistant in a container loses memory and keys on every upgrade unless the volumes are set up right. **The outcome:** Qwen Paw's console on 127.0.0.1:8088 with config, memory and skills kept across restarts. ### Steps 1. Run `docker pull agentscope/qwenpaw:latest` 2. Start it with the README's docker run command, mapping 127.0.0.1:8088 and the qwenpaw-data, qwenpaw-secrets and qwenpaw-backups volumes 3. Open http://127.0.0.1:8088/ for the console 4. If your models run in Ollama on the host, use the README's host binding note because localhost inside the container is the container itself ### Prompt to paste into your agent ```text Deploy agentscope-ai/QwenPaw with Docker on using the README's run command and the three named volumes, connect it to Ollama on the host, and confirm memory survives a container restart. ``` ### Caveat Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/agentscope-ai-qwenpaw/deploy-qwenpaw-in-docker-with-persistent-volumes/ ## How to schedule a daily news digest sent to Telegram or Discord with Qwen Paw Repo: [agentscope-ai/QwenPaw](https://github.com/agentscope-ai/QwenPaw) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Use Qwen Paw's scheduling and multi-channel features to push a recurring summary to your chat apps. **Who it is for:** A person or small team that wants a morning digest delivered where they already chat. **The problem:** Checking several sources every morning is tedious, and most digest tools only send email. **The outcome:** A recurring digest that Qwen Paw writes and posts to the channels you choose. ### Steps 1. Set up Qwen Paw and connect your Telegram or Discord channel in the console 2. Enable the news and scheduling skills 3. Create a recurring task: the topics, the time and the target channel 4. Read the first few digests and adjust the sources or length ### Prompt to paste into your agent ```text In agentscope-ai/QwenPaw, connect my channel and create a scheduled task that posts a short digest of every day at