Skip to content
JevDirectory.org
CommunityTools & Integrations3.1k starsVerified 2026-09-22

Jev 聊天助手

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.

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

Highlights

  • Jev returns the counterpart's intent, a 1-9 danger level, what they want, whether to reply now, and the best action in about a second.
  • A generation model drafts three replies and Jev ranks them; the app only fills the input box and never taps send or touches payments.
  • Reads the screen through the system accessibility service, not hooks or app APIs; Lark uses on-device ML Kit Chinese OCR for its drawn text.
  • Coverage is author-reported: WeChat 8.0.78 full chain, QQ 9.3.50 group chat, X DMs 12.25 in Chinese; QQ 1v1 and the English X UI are unverified.
  • Judgment, reply, and vision endpoints are configured separately with presets for OpenRouter, TypeSafe direct, DeepSeek, and Tongyi-compatible APIs.

Quickstart

bash
adb install -r apk/jev-assistant-v1.3-release.apk

Watch out

MIT-licensed and Android 11+ only. Needs accessibility, overlay, and autostart permissions plus your own API key; chat content goes to the model endpoints you configure, and only WeChat, QQ, and X are fully adapted.

More like this

Mobile Jev
340GitHub stars
Standalone Android agent and React studio for Mobilerun, powered by Jev: Jev selects operations and observed targets, code rejects stale actions, and a CLI, execution traces, and latency measurements ship in the repo. No ADB connection required.
Tools & Integrations#community#javascript#agents
Communitymobile-jev
jev-mobile
4GitHub stars
Experimental Android sub-agent that gives Jev a bounded list of technically valid UI actions per step, with requirement-driven subgoals, durable SQLite tasks, confidence gates and escalation instead of coordinates.
Tools & Integrations#community#python#agents
Communityjev-mobile
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
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Fast browser use with Stagehand

Kyle Jeong
Kyle Jeong
Browserbase
@kylejeong
·

we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more

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 30 replies

LLM-as-a-judge, sped up

Yuchen Jin
Yuchen Jin
Databricks
@Yuchenj_UW
·

Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)

Image
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 94 replies

Instant compaction with Jev

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 137 replies

Jev lands on OpenRouter