ai-goofish-monitor
by Usagi-org
A self-hosted web app that uses a browser automation tool and an AI model to watch listings on Xianyu (Goofish), a Chinese second-hand marketplace. It runs several search tasks on a schedule, has the AI judge each item and sends an alert when something matches your criteria.
- Stars
- 16k +106 a day
- Licence
- MIT
- Runs on
- A small server
- Setup
- Moderate
- Language
- Python
- Age
- 475 days
What you can do with it
- Set up several keyword searches with price, region and posting-time filters and run them on a schedule
- Describe in plain language what a good deal looks like and let an AI model assess listings, including photos
- Receive alerts through ntfy, WeCom, Bark, Telegram or a webhook when a suitable item appears
Make money with it
Someone could use it to find undervalued second-hand goods and resell them, or offer a deal-sourcing alert service to other buyers.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Spot underpriced second-hand items on Xianyu to buy and resell at a profit
- Track market prices for particular products to help with sourcing or pricing decisions
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Clone the repository, copy .env.example to .env, add your AI model details, then start it with docker compose up -d; you also need to export your Xianyu login state using a Chrome extension.
Follow the official instructions in the project README.
Things to check
- Needs a paid AI model API key that accepts image input
- Scrapes Xianyu using a logged-in account, which may breach its terms and could get the account restricted
- Default web login is admin/admin123 and must be changed
- Documentation and the target marketplace are in Chinese
- Authors state it is for learning and research use only
Checked 03 Nov 2026. Summary drafted by AI from the project's README.
