User repository on GitHub
A working Demo that acts as classifier to classify linkedin post which inside uses jev by Typesafe.ai
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
CommunityJev Demos & Experiments
Postmark
Next.js demo that reads a draft social post and returns three typed reads from one Jev call: tone as a Choice, virality as a 0 to 3 Score, cringe risk as a Noul, plus a verdict stamp.
- Stars
- 2
- Language
- TypeScript
- License
- MIT
- Published by
- Community
- Author
- silky-x0
- Last verified
- Oct 2026
About this project
Postmark is a tiny web app that reads your draft social post before you publish it and tells you how it might land. You paste in some text, hit one button, and it comes back with three honest reads: what tone you are giving off, how far it might travel, and whether it might make people cringe a little. It is meant to feel like asking a blunt friend, except the feedback comes back as clean numbers and bars you can actually use in code.
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- TypeScript
Highlights
- All three questions run in parallel from one call; the API route builds the payload and forwards it with a bearer token.
- The verdict is client-side if/else on two thresholds: cringe at 0.6 or above, otherwise virality at 2.2 or above.
- The page never calls TypeSafe directly, so the key stays server-side; missing key returns 500, bad drafts return 400.
- Results render as probability bars, tone sorted high to low and virality by level, so nothing has to be parsed from prose.
Watch out
The author is explicit that this is a demo built to show structured answers, and the lib folder is empty. The rubrics are fixed input, not learned measurement: six named tone criteria, four ordered virality levels from Ignored to Breakout, and hardcoded 0.6 and 2.2 cutoffs that live in the client, where anyone can change them in devtools. No calibration data is published for any of the three scores. The tone question defines six criteria today while the README also claims a tone renamed upstream would appear without a code change, which is worth testing before relying on it. Upstream 429 and 529 pass through and other upstream failures map to 502, with the error shown under the draft box; no retry logic is documented. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
They are the model's answers to rubrics you supply, not a validated measurement. Tone picks from six fixed criteria, virality is an ordered four-level scale, and the verdict is two thresholds you could change to anything. Nothing in the README reports agreement with human judgement, so treat the numbers as a prompt for your own rewrite rather than a score to optimise.
Yes. The API route posts the draft to the TypeSafe systemone endpoint with a bearer token, and the draft is the state being judged. What stays local is the key: the page never calls TypeSafe directly, so TYPESAFE_API_KEY is read from the server environment in .env.local, which the project expects you to create from .env.example.
The README's argument is that typed answers remove repair code: with choice plus probabilities plus confidence and score plus legend plus probabilities you can sort, draw bars, compute a verdict or gate a publish button without regex or JSON repair. Its stated weak spots for normal chat models are token-by-token latency, paying for output you discard, schema drift even in JSON mode, and overkill when you only need three values.
Drafts must be non-empty after trimming and 2000 characters or less; the textarea allows 2200 so the over-limit message appears before the button disables. If the key is missing you get a 500 with a message about .env.local, and if TypeSafe is down or the key is wrong the error text renders under the draft box instead of failing silently. Rate limit statuses pass through and other upstream failures become 502, with no documented retry.
You need Node 20 or newer and a TypeSafe API key. Run npm install, copy .env.example to .env.local, add TYPESAFE_API_KEY, then npm run dev and open http://localhost:3000. Other commands are npm run lint, npm run build and npm start.
Tone is a Choice over hot take, humble brag, inspirational, informative, funny and vulnerable. Virality is a Score from 0 to 3 across Ignored, Mild, Solid traction and Breakout. Cringe risk is a Noul between 0 and 1. All three run in parallel from one API call.
The API accepts a trimmed draft of up to 2000 characters and returns 400 for an empty, missing or longer draft. The textarea allows 2200 so you see the over-limit message before the button is disabled.
More Jev resources like this
98GitHub stars
Self-hosted Docker service and web UI that packages Laya structured-decision inference behind a compatible System One endpoint.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
1Panel-dev/laya-serverPython
1Panel-dev/laya-serverPython20GitHub stars
General-purpose System One agent where Jev chooses tools and arguments while Jot executes them and loops until it can reply.
Jev Demos & Experiments#community#awesomejev#catalog-import
Community
runta-dev/jotTypeScript
runta-dev/jotTypeScript23GitHub stars
Browser drone-fleet lab where TypeSafe Jev steers each drone as fast reflexes and an optional planner offers one-use strategy advice when confidence drops, without pausing control.
Jev Demos & Experiments#community#jevbest#catalog-import
23GitHub stars
Chrome extension that sends each X post to Jev with six typed questions in one call near the viewport, then renders a behavior chip under the post plus a session cost and latency panel.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
oso95/x-scannerTypeScript
oso95/x-scannerTypeScript14GitHub stars
Manifest V3 Chrome extension in TypeScript that sends each LinkedIn post to Jev and collapses bait, self-promo, off-topic, and sponsored posts into a one-line bar with reasons and scores.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
stefw/lkcleanTypeScript
stefw/lkcleanTypeScript11GitHub stars
Standalone Flue example that routes support chat through Cloudflare Workers AI, using gpt-4o-mini for chat and Jev for typed intent and urgency routing.
Jev Demos & Experiments#community#awesomejev#catalog-import
Community
matthewp/flue-jev-demoTypeScript
matthewp/flue-jev-demoTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
From the Jev community
Posts from builders shipping with Jev right now.