wechat-mac-rpa — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by wq19901103wq · Agent Tool · ★ 113

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is wechat-mac-rpa safe to install? View the security audit →

About wechat-mac-rpa

WeChat Mac RPA 中文 | English 让 AI 像人一样"看"着微信界面,自动回复消息。默认 OCR / SmartPipeline 模式不碰协议、不读数据库、不注入代码;可选 WeFlow 模式会读取用户授权的本地数据库副本,用于初始化历史记忆。 基于多模态视觉感知与LLM Agent的 macOS 微信自动化框架。默认模式不是协议逆向或 Hook,而是把微信当作纯黑盒 GUI 应用:用计算机视觉读取界面,用大语言模型理解对话,用系统级自动化操作界面。 核心设计:感知 → 推理 → 行动 → 记忆 → 数据飞轮,五个子系统构成完整的认知闭环。每一次认知循环的完整链路都被结构化日志逐条记录,形成可追溯、可回归、可量化的生产质量资产。 快速开始 环境:macOS 12+,Python 3.10+,微信 Mac 版 依赖: 配置:复制 为 ,填入 API Key;复制 为 ,填写本地人设 隐私: 与 默认不进入 Git;不要把 API Key、聊天记录或真实人设提交到仓库 权限:Bot 依赖 macOS 辅助功能/屏幕录制权限,详见下文权限说明 启动: 管理后台(LaunchAgent 常驻): bash # 首次加载(用户登录时自动启动,崩溃自动重启) launchctl bootstrap gui/$(id -u) /Library

agentai-agentai-automationapple-scriptautomationchatbotcomputer-visiondesktop-automationdigital-twingui-automation

Quick Facts

Stars113
Forks33
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score64.0209455497516/100
Open Issues5
Last Updated2026-10-03
Created2026-05-02
Platformspython
Est. Tokens~17k

Compatible Skills

These tools work well together with wechat-mac-rpa for enhanced workflows:

  • Auto-Use — semantic(0.28)+complementary+rare_topics+same_lang+similar_pop+shared_platform (73%)

wechat-mac-rpa alternative? Top 6 similar tools

Looking for a wechat-mac-rpa alternative? If you're comparing wechat-mac-rpa with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • CodexBridge by Gan-Xing · ⭐ 415

    WeChat-to-Codex bridge for running Codex app-server from chat, with threads, slash commands, approvals, agents

  • clawdcursor by AmrDab · ⭐ 403

    clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addr

  • wechat-rpa-bot-skill by LeoMusk · ⭐ 78

    专为 AI 智能体设计的强大微信 RPA 技能,支持无头运行与 REST API 控制,打破大模型与真实微信操作的鸿沟

  • rosclaw by ros-claw · ⭐ 208

    Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evo

  • os-ai-computer-use by 777genius · ⭐ 181

    AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app

  • openpaw by daxaur · ⭐ 157

    Personal Assistant Wizard for Claude Code — npx pawmode

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is wechat-mac-rpa?

wechat-mac-rpa is 基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat. It is categorized as a Agent Tool with 113 GitHub stars.

What programming language is wechat-mac-rpa written in?

wechat-mac-rpa is primarily written in Python. It covers topics such as agent, ai-agent, ai-automation.

How do I install or use wechat-mac-rpa?

You can find installation instructions and usage details in the wechat-mac-rpa GitHub repository at github.com/wq19901103wq/wechat-mac-rpa. The project has 113 stars and 33 forks, indicating an active community.

What license does wechat-mac-rpa use?

wechat-mac-rpa is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to wechat-mac-rpa?

The top alternatives to wechat-mac-rpa on Agent Skills Hub include CodexBridge, clawdcursor, wechat-rpa-bot-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools