Skip to content
JevDirectory.org
CommunityTools & Integrations210 starsVerified 2026-09-22

jev-chat-windows

A Windows WeChat side panel that reads the visible conversation with local RapidOCR, has Jev judge intent and tension and rank three reply candidates, then fills the chosen one into the input box; sending is always manual.

Open github.comjev-chat/jev-chat-windows
Category
Tools & Integrations
Published by
Community
Author
jev-chat
Added
2026-09-22
Tagscommunitypythonwindowswechatprivacy

Highlights

  • Jev judges intent and tension 0 to 9 and ranks three candidates via OpenRouter (typesafe/jev-1.13) or TypeSafe direct (jev-latest); a second LLM drafts them.
  • Capture is WGC window screenshots plus offline RapidOCR only: no hooks, injection, WeChat database reads, or process-memory access.
  • Screenshots live only in memory, and only two keys exist — JEV_API_KEY and LLM_API_KEY — stored in the HKCU\Environment registry.
  • Models are called only when a new incoming message arrives, so ten quiet minutes means zero tokens; the program never presses send and avoids payment UI.
  • Requires Windows 10 1903+ or 11 and WeChat Windows 4.x; the prebuilt release zip is about 146 MB and its executable is unsigned.

Quickstart

bash
pip install -r requirements.txt pyinstaller
pyinstaller --noconfirm --clean jev.spec

Watch out

The project's own code is MIT with a NOTICE, but the shipped PyInstaller bundle includes GPLv3 PySide6-Fluent-Widgets, so the release package is GPLv3-bound and commercial use needs a separate license.

More like this

jev-chat-jarvis (macOS)
142GitHub stars
A macOS floating panel that reads visible WeChat messages through OCR, has a local decider model or TypeSafe Jev classify intent and risk from 0 to 9, then generates and reranks reply candidates without injecting anything into WeChat.
Tools & Integrations#community#python#macos
Communityjev-chat-jarvis-mac
Jev Ultrafast
17.5kGitHub stars
Browser Use's ultrafast agent: Jev picks an operation and an element from an indexed action space in one request, and a small LLM writes text only when the action is TYPE_TEXT.
Tools & Integrations#community#python#browser
Communityjev-ultrafast
Jev 聊天助手
3.1kGitHub stars
An Android overlay that reads visible WeChat, QQ, and X conversations through accessibility, asks Jev for intent, danger, and the best action, then drafts three replies and fills one in without ever sending it.
Tools & Integrations#community#kotlin#android
Communityjev-chat-jarvis
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A million judged questions

Inferring Jev's internals from 1,000 calls

iwashi / Yoshimasa Iwase
iwashi / Yoshimasa Iwase
@iwashi86
·

Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more

Reply
Read 2 replies

The open System One roundup

小墨同学
小墨同学
@xiaomovps
·

Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格

Image
Reply
Read 6 replies

The launch post

Trading bot, one decision per block

Classifying 1,500 real emails

vogel
vogel
Anomaly
@ryanvogel
·

this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 69 replies