How many free reviews do I get before needing a key?

The server key covers a small number of demo reviews per browser. After that you enter your own TypeSafe key in the form for that request, and rerunning unchanged inputs reuses the visible result without a new call.

What happens to my resume text and API key?

Extracted resume text and role context are sent to TypeSafe for scoring. The app does not save resumes or results, and a key you enter is used for that request rather than stored.

Will it read my scanned PDF directly?

Recreate the text first with OCR, since scanned PDFs need that step before upload. The accepted inputs are PDF, DOCX, and TXT through the local dev flow with install, env copy, and dev server.

Can I rely on the demo cap for a public deploy?

Clearing cookies or restarting and scaling the server can shift the effective limit, so public deploys should add provider-side budgets and a shared rate-limit store instead of relying on the cookie and memory cap.

What exactly comes back from a review?

An overall score, the individual criteria, a score per experience bullet, and a suggested bullet order for the resume to follow. The rubric that produced those criteria is recorded separately in docs/resume-prompt.md, and docs/how-it-works.md explains the review pipeline and where to experiment in code.

How does the demo allowance actually work?

Two layers. The browser gets a signed job_match_demo cookie for five free reviews, and the server holds an in-memory cap of 40 shared-key calls per process per UTC day. Opening /api/review in the same browser returns remaining and demoAvailable so you can inspect the state, and clicking Check resume again with unchanged inputs keeps the visible result and issues no new request.

What do I need to run it locally?

pnpm install, then copy .env.example to .env.local, set TYPESAFE_API_KEY, and run pnpm dev and open the URL the terminal prints. The entry is listed as a new package on npm in the repo README; the footer still links to the author's profile with a note to replace it once the repository is published.

CommunityJev Demos & Experiments

Jev Resume Match

Resume review app that takes a PDF, DOCX, or TXT plus a target role and optional job description, then returns an overall score, criteria, bullet scores, and ordering.

See highlights

Open github.com

Stars: 5
Language: TypeScript
Published by: Community
Author: hamidfarmani
Last verified: Oct 2026

hamidfarmani/jev-resume-match

User repository on GitHub

View on GitHub

Score how well a resume matches a job description using Jev (TypeSafe AI). Next.js app that returns typed, explainable match scores instead of generated text.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

A simple resume review app. Upload a PDF, DOCX, or TXT file. Add the role you want and, optionally, a job description. The review shows an overall score, individual criteria, experience bullet scores, and a possible bullet order. Copy .env.example to .env.local and set TYPESAFEAPIKEY. Run pnpm dev and open the local URL shown in the terminal.

Quoted from the project's README. Read the full README.

Tagscommunity awesomejev catalog-import

Works forJev for Classification Jev for Ranking

Used inJev for Software & DevTools

Languages: TypeScript

Highlights

Scores a resume against a role with per-criterion results, per-bullet scores, and a suggested bullet order.
Accepts PDF, DOCX, and TXT with an optional job description alongside the target role.
Reuses the visible result when inputs are unchanged so repeat clicks do not spend another review.
Exposes demo allowance at the review API with remaining count and availability flags.

Watch out

Demo use is capped by a signed browser cookie and a shared in-memory daily limit, which is a small-project safeguard rather than a spending control. 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.

More Jev resources like this

x-scanner

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

tweet-911

A Chrome extension that scores X posts and replies as they enter the viewport, judging the author's handle, display name and bio alongside the post text and, for replies, the parent post.

Jev Demos & Experiments#community#awesomejev#catalog-import

Community

elliothux/tweet-911TypeScript

magic-jev-ball

A Magic 8 Ball that picks with Jev instead of at random. Hold, shake, release, and Jev chooses from the twenty classic answers and returns a probability for each one, shown under the ball.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

mikecann/magic-jev-ballTypeScript

jevplay

JevPlay is a playground for TypeSafe Jev: a freeform state block plus a builder for custom Choice, Score and Noul questions, showing live probability distributions as you write them. Setup is npm i and npm run dev.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

ndolinschi/jevplayTypeScript

sift

Chrome extension that re-ranks Google results with TypeSafe Jev: five atomic questions per result, a weighted score, sales pages flagged and hidden, and a button to restore Google's order.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

tylergibbs1/siftTypeScript

Jev-test

A TypeScript CLI and Fastify service that puts three questions about an occupation to Jev in one request - layoff risk, trajectory and human accountability - and derives a resilience score in app code.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

WeSecureYou/Jev-testTypeScript

From the Jev guides

Original write-ups on what this entry is for.

Per-Tick Decisions in Games

Sep 28, 2026

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

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai