OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Workflow Agents

Xianyuautoagent

XianyuAutoagent is a self-hosted Python agent for automating Xianyu marketplace customer-service conversations. It uses an LLM and stored conversation history to draft contextual replies, routes inquiries to specialist prompts for customer service, technical support and bargaining, and supports stepwise price reductions and network search.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Xianyuautoagent — OpenViST project profile in Workflow Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to configure and run an LLM-based responder for Xianyu conversations from a Python environment, with distinct prompts for different inquiry types.

Who it is for

  • Xianyu sellers or operators seeking to automate customer inquiries from a locally run tool.
  • Python developers who want to configure model access, marketplace cookies and specialist reply prompts.

Documented uses

  • Draft customer replies using the conversation history as context.
  • Route inquiries among customer-service, technical-support and bargaining specialists.
  • Configure stepwise price-reduction responses.
  • Use network search to support technical answers.
  • Switch between AI handling and human takeover using configurable keywords.
Before you choose

Requirements & limits

The project is a public GitHub repository identified as GPL-3.0 licensed. Its documented use is local: configure model credentials and a Xianyu web cookie, then run the Python entry point.

  • Requires Python 3.8 or later, model API configuration and a Xianyu web cookie.
  • Tongyi Qianwen is the default model; using another API entails changing the model URL and name.
  • Custom prompts can be provided for classification, pricing, technical support and default replies; template defaults are available.
  • The README marks market price comparison, RAG knowledge-base enhancements and a web management interface as planned rather than implemented.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Configure and start the local agent

Set up the documented Python environment and launch XianyuAutoagent.

Before you start

  • Python 3.8 or later
  • An API key, model base URL and model name
  • A Xianyu web cookie
  • The repository and its requirements file

Steps

  1. Clone the repository and change into its directory.

  2. Install dependencies with pip install -r requirements.txt.

  3. Create a .env file with API_KEY, COOKIES_STR, MODEL_BASE_URL and MODEL_NAME; the README also permits renaming .env.example.

  4. Optionally add or rename prompt templates in prompts/, then start the program with python main.py.

Expected outcome

The local main.py program starts with the configured model and Xianyu cookie settings.

Guide limitations

  • The README names Tongyi Qianwen as the default model and says other APIs require changing model settings.
  • The guide documents setup and program launch; it does not establish successful operation or compatibility with other providers.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
shaxiu/XianyuAutoAgent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction