# Liyucheng1997/332_lab-jev-chat

> A non-invasive chat assistant: it reads on-screen conversations (Android via Accessibility, Windows via UI Automation or OCR), the Jev model judges intent and risk, a generative model drafts 3 replies shown in an overlay and filled into the input box without sending.

- Magnitude: 4.8 out of 10 — Early signal
- Stars: 106 total · +12 stars today, ≈ 34 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Kotlin · License: MIT · Created: 2026-09-21 · Last push: 2026-09-21
- GitHub: https://github.com/Liyucheng1997/332_lab-jev-chat · Page: https://gitnova.dev/en/r/Liyucheng1997/332_lab-jev-chat

## Useful for

- Get reply suggestions overlaid on WeChat on Android or Windows
- Assess the intent and risk level of an incoming message before replying
- Add an adapter for a new messenger in ChatAppAdapter.kt

## Why it’s here

- 12 stars so far today, about 34 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 2 days old and already has 106 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- About 12 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 12
- Issues and pull requests: 6
- Watchers: 0
- Average over the last week: 43 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0
- Latest release: v1.0.0 (2026-09-21)

## Stars per day, last 4 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-23: 0, 2, 92, 12

## Similar by description

1. **jev-chat/jev-chat-jarvis** — 8.3 · Breakout · AI agents · Kotlin · +505 stars today, ≈ 1,209 by evening
   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 sent manually.
   Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-jarvis.md
2. **jev-chat/jev-chat-jarvis-mac** — 6.5 · Early signal · AI agents · Python · +42 stars today, ≈ 96 by evening
   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.
   Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-jarvis-mac.md
3. **jev-chat/jev-chat-windows** — 6.6 · Early signal · AI agents · Python · +65 stars today, ≈ 142 by evening
   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 manual.
   Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-windows.md
4. **FerryCorleone/crush-monitor** — 3.8 · Early signal · AI agents · TypeScript · +15 stars today, ≈ 31 by evening
   A local web tool that analyzes WeChat chat logs copied from the app using the Jev model: it shows emotions, intents, a liking-signal score and grades your own replies. Runs on your machine with your own TypeSafe API key.
   Full card: https://gitnova.dev/en/r/FerryCorleone/crush-monitor.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-23 13:41 UTC, updated every 30 minutes.