# Prinsphield/Wechat_AutoJump

AI plays WeChat Jump Game

Repository: https://github.com/Prinsphield/Wechat_AutoJump
Canonical: https://ross.abutalabs.com/products/wechat_autojump
Homepage: https://zhuanlan.zhihu.com/p/32636329
Language: Python
License: MIT
License Family: permissive
Last push: 2019-11-21T17:37:39+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3168, "days_push": 2477, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1280, forks 408 (observed 2026-08-28T04:04:13.635589+00:00)

## What it is
A Python bot that automatically plays the WeChat 'Jump Jump' mini-game using computer vision and a CNN coarse-to-fine model to locate the player and target. It controls an Android or iOS phone over USB via adb or WebDriverAgent to time presses.

## Use cases
- automatically play the WeChat jump game on my phone
- bot that plays tiaoyitiao for high scores
- use a CNN to detect game character and target positions
- learn how to build a phone game bot with opencv and tensorflow
- automate taps on an android game via adb

## When to avoid
- you need a maintained tool - the project has not been updated since 2019
- you want to automate games other than WeChat Jump
- you need a solution that works without a USB-connected phone

## Facets
- artifact type: application
- maturity: abandoned
- function: computer-vision, machine-learning, deep-learning, image-processing
- domain: gaming-tools, computer-vision, deep-learning
- platform: python
- tags: wechat, jump-game, game-bot, cnn, adb, screen-capture, game-automation, automation, android, ios, macos

## Member repositories
- Prinsphield/Wechat_AutoJump (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.635589+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:02:35.311822+00:00, confidence not recorded.
  - readme: https://github.com/Prinsphield/Wechat_AutoJump (fetched 2026-08-28T04:04:13.635589+00:00, sha c928390e35ba)
- Data as of 2026-08-30T08:39:29.467469+00:00.