jev-chat/jev-chat-jarvis-mac
微信消息意图识别悬浮窗(macOS):看屏 + 本地小模型判断意图和风险,再按话术生成回复候选。纯只读、不注入微信。
About the project
A macOS app that OCR-reads WeChat messages on screen and uses a local model to classify intent and risk, suggesting reply candidates. Read-only, with no injection into WeChat.
Useful for
- Check the intent and risk of an incoming WeChat message before replying
- Generate reply drafts in different tones and copy the suitable one
- Run the local decider-2b model for offline analysis without sending data online
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 80 stars so far today, about 132 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 1 day old and already has 139 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #142.
- About 80 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 139
- Today
- 80 · ≈ 132 by evening
- Forks
- 37
- Issues and pull requests
- 39
- Watchers
- 0
- Language
- Python
- License
- MIT
- Latest release
- v0.4.0 · September 22, 2026
- Created
- September 21, 2026
- Last push
- September 22, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 22, 2026Top new repositories this week: #142
Similar by description
-
6.0
jev-chat/jev-chat-windows
A reply helper for WeChat on Windows: it captures the window, reads incoming messages with offline OCR, infers the other person's intent, and offers 3 candidate replies to insert into the input box. Sending is always…
-
8.3
jev-chat/jev-chat-jarvis
Android app that reads the on-screen chat via AccessibilityService, judges the other side's intent with the Jev model, and shows 3 ranked reply drafts in a translucent overlay. Replies are filled into the input box but…