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 jev-chat · LLM Plugin · ★ 728
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is jev-chat-windows safe to install? View the security audit →
jev-chat-windows 微信（Windows 4.x）旁挂的回复辅助：本地 OCR 读屏上的对话 → Jev 判断意图/情绪 → 给出 3 条候选回复 → 一键填入微信输入框。发送永远手动，程序不替你按发送。 判断内核来自安卓版 Finderchangchang/jev-chat-JARVIS， 这里把采集换成了 Windows 端的窗口截图 + 离线 OCR。 下载即用（推荐） 普通使用直接下载，不用装 Python、不用碰源码。 后面的「源码运行」是给开发者的。 👉 下载最新版 在 Releases 页下载 （约 146 MB） 解压到一个固定目录（整个文件夹一起，exe 要用旁边那堆文件） 双击 要求：Windows 10 1903+ / 11，微信 Windows 4.x，一个 OpenRouter API key（openrouter.ai）。 首次启动会弹设置页填 OpenRouter API key。两个 key 都写进 Windows 用户环境变量（注册表 ）， 不落任何文件；其余设置写在 exe 旁边的 ，整个文件夹拷走设置也跟着走。 exe 没签名，SmartScreen 会拦一下：「更多信息」→「仍要运行」。介意就往下看「自己打包」，自己打的更踏实。 使用说明 第一次启动 弹出的设置页里填 OpenRouter API key（openrouter.ai 申请）。这个必填： 判断意图、紧张度、给三条候选排序的 Jev 模型（）只在 OpenRouter 上有。 选「你们的关系」（恋人 / 朋友 / 同事 / 家人 / 自定义），保存。可以用了。 国内用户强烈建议：起草切到 DeepSeek 直连 起草三条候选默认也走 OpenRouter，但 OpenRouter 在国外，从国内过去这一步要等好几秒、还时不时抽风。 DeepSeek 官方 API（）国内直连，起草基本就是一次 HTTP 请求的时间，体感差好几倍： 去 platform.deepseek.com 申请一个 key（很便宜，起草一次几厘钱） 设置页「回复服务」→「起草模型来源」选 DeepSeek 直连，填 DeepSeek key，保存 Jev 判断那一步仍然走 OpenRouter，它比起草轻得多，慢一点无所谓。两个 key 都只进注册表，不落文件。 日常怎么用 微信开着、别最小化（用别的窗口盖住没事），把要聊的会话点开 对方来一条消息 → 悬浮窗几秒后给判断摘要 + 三条候选（带 Jev 给的胜出概率） 点「填入微信」→ 文字进微
| Stars | 728 |
| Forks | 159 |
| Language | Python |
| Category | LLM Plugin |
| Quality Score | 60.7356191435954/100 |
| Open Issues | 26 |
| Last Updated | 2026-09-28 |
| Created | 2026-09-21 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with jev-chat-windows for enhanced workflows:
Looking for a jev-chat-windows alternative? If you're comparing jev-chat-windows with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI gets the context. Not your private data. Local-first privacy proxy for browser chat, AI APIs, and coding ag
MCP server that lets Claude Code and other AI agents read and search large PDFs, one file or a whole folder: a
情圣 · Claude Code 中文恋爱教练技能 · 微信/探探/Soul/Bumble/青藤之恋聊天截图分析 · 高情商回复生成 · 7阶段关系推进
A local MCP server for agent literature work. Original-LaTeX section reads, BibTeX from arXiv metadata, and to
Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - c
AI as Workspace - An elegant AI chat client. Full-featured, lightweight. Support multiple workspaces, plugin s
Explore other popular llm plugin tools:
jev-chat-windows is JevChat-Windows：聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入，发送永远手动. It is categorized as a LLM Plugin with 728 GitHub stars.
jev-chat-windows is primarily written in Python. It covers topics such as chat-assistant, jev, llm.
You can find installation instructions and usage details in the jev-chat-windows GitHub repository at github.com/jev-chat/jev-chat-windows. The project has 728 stars and 159 forks, indicating an active community.
The top alternatives to jev-chat-windows on Agent Skills Hub include pasteguard, pdf-mcp, qingsheng-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: