Analysis updated 2026-05-18
Automate keyword based replies to buyer questions on a Xianyu shop.
Confirm shipment automatically once a payment message is detected.
Manage multiple Xianyu seller accounts from one web dashboard.
Bulk refresh product listings on a schedule to improve visibility.
| gudong2003/xianyu-auto-reply-fix | oranai-ltd/oransim | google-research/tabfm | |
|---|---|---|---|
| Stars | 1,084 | 1,102 | 1,041 |
| Language | Python | Python | Python |
| Last pushed | — | — | 2026-07-03 |
| Maintenance | — | — | Active |
| Setup difficulty | moderate | moderate | moderate |
| Complexity | 3/5 | 3/5 | 3/5 |
| Audience | developer | pm founder | data |
Figures from each repo's GitHub metadata at analysis time.
Needs Docker or a Python 3.11 plus Node.js environment, plus Xianyu account cookies to connect.
xianyu-auto-reply-fix is a management system for Xianyu, also known as Goofish, a popular secondhand marketplace app in China similar to a local classifieds and resale platform. The project gives sellers a full backend to run their shop operations without having to sit and reply to buyers all day. The system is built with Python 3.11 and FastAPI on the backend, with a SQLite database and a Bootstrap based web interface up front. It communicates in real time using WebSocket and Server Sent Events, and it uses browser automation, Playwright and DrissionPage, to interact with Xianyu directly, since the platform does not offer an official API for this kind of automation. Sellers can manage multiple Xianyu accounts from one dashboard, each kept fully separate with its own data and login. The AI powered auto reply feature matches keywords to product listings so buyers get relevant answers automatically, with a priority order that checks product specific replies first, then product category keywords, then general keywords, then a default reply, and finally an AI generated reply if nothing else matches. The system can also detect when a buyer has paid and automatically confirm shipment, matching the right delivery details to the right listing and avoiding duplicate confirmations. Other features include bulk listing refresh so items appear higher in search results, scheduled daily refresh windows with random delays to look more natural, product and coupon data management with Excel import and export, operation logs, and health check endpoints. The whole thing can be deployed with a single Docker Compose command, or run locally with a Python virtual environment. The project author states clearly that this is for study and research purposes only and that commercial use is strictly prohibited. Before using it, read the license terms in the README carefully. The full README is longer than what was shown.
A self-hosted dashboard that automates replies, shipping confirmation, and multi-account management for sellers on Xianyu, a Chinese secondhand marketplace app.
Mainly Python. The stack also includes Python, FastAPI, SQLite.
Study and research use only, the author strictly prohibits commercial use.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.