Skip to content
JevDirectory.org
CommunityTools & Integrations1 starsVerified 2026-09-22

Jev Wrapped

Telegram channel X-ray that judges up to 1,500 public posts from the last year with one Jev Choice over ten post kinds and three Noul checks, then draws a shareable monthly mix card.

Open github.comgaborishka/jev-wrapped
Category
Tools & Integrations
Published by
Community
Author
gaborishka
Added
2026-09-22
Tagscommunityjavascriptcloudflaretelegramopenrouter

Highlights

  • Each post with text gets its own Jev request with four typed questions: kind (one of ten), paid ad, clickbait and emotional pressure.
  • A 1,500-post channel takes 35 to 85 seconds and costs about $0.10 at list price; posts without text are counted as media only.
  • Reaches Jev through TypeSafe's API (2 pages at a time) or OpenRouter's alpha Decisions API (4 at a time, about 35 s).
  • Posts come from Telegram's public t.me/s preview with no login or bot API; the id from a year ago is found by bisection.
  • The card is one SVG string and the link preview is drawn pixel by pixel into a palette PNG with a 5x7 bitmap font, about 6 KB.

Quickstart

bash
git clone https://github.com/gaborishka/jev-wrapped.git
cd jev-wrapped
npm install
cp .env.example .env
npm run dev

Watch out

MIT-licensed. Needs Node 22+, a TypeSafe or OpenRouter key and a Cloudflare account with D1; every fresh run spends your key, and daily run and budget ceilings are set with env vars.

More like this

Jev for Chrome
18GitHub stars
Unofficial Chrome Manifest V3 port of browser-use/jev-ultrafast: Jev picks the operation and DOM element in one request, a small text model writes typed values, and the run happens in your own tab with your logins. Ships a 17-task headless-Chromium suite.
Tools & Integrations#community#typescript#chrome-extension
Communityjev-for-chrome
Jev Agent Browser
8GitHub stars
Delegated browser execution for parent agents: Jev picks one bounded typed action from the current page snapshot, agent-browser performs it, and ambiguous or stuck flows escalate back to the parent.
Tools & Integrations#community#javascript#browser
Communityjev-agent-browser
Jev-cu
571GitHub stars
An experimental Codex skill and JavaScript runtime that has Jev pick macOS Accessibility elements and actions from text candidates, while local policy gates hold sensitive operations for human confirmation.
Tools & Integrations#community#javascript#codex
CommunityJev-cu
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

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

700 leads scored for $0.09