User repository on GitHub
이름으로 나이대를 맞히는 React 웹 (TypeSafe Jev)
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Guess the Age from a Korean Name
A small React web app where Jev, TypeSafe's System One API, estimates a name's age band and gender from naming trends across Korea, the US, Japan and China. A Vite server plugin keeps the API key server-side and the UI draws the returned band probabilities as bars.
- Stars
- 1
- Language
- TypeScript
- Reading time
- 2 min
- Published by
- Community
- Author
- ximhear
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- TypeScript
- Platforms
- Browser
- Capabilities
- Open sourceRequires API key
Highlights
- Pick a country (Korea, the US, Japan or China) and type a name; the app shows a probability distribution over age bands plus a gender estimate.
- server/predict.ts sends two choice questions per request — age band and gender — through @typesafe-ai/sdk.
- The API key lives only on the server: a Vite dev/preview plugin exposes /api/age, and the browser never sees TYPESAFE_API_KEY.
- The README ships an eight-name demo video (demo/name-age-demo.mp4) showing the bars for each example name.
- src/countries.ts holds per-country input rules, naming-trend hints and example names shared by the UI and the server.
Quickstart
bash
npm install
cp .env.example .env
npm run devWatch out
Grounded in the Korean-language README and GitHub metadata reviewed on 2026-10-15; the repository shows 1 star and no license in the metadata, and the README documents no tests, accuracy figures or costs. Any claim about how well Jev guesses age bands is not backed by a published evaluation in the captured material.
Questions about this entry
Short answers drawn from the linked project or page.
You choose a country (Korea, the US, Japan or China) and enter a name; Jev, TypeSafe's System One model, estimates the age band and gender from era-specific naming trends, and the UI renders the age-band probabilities as bars.
The server sends two choice questions per request — age band and gender — to the System One API through the @typesafe-ai/sdk. Per-country input rules, naming-trend hints and example names live in src/countries.ts, shared between the UI and the server.
Run npm install, copy .env.example to .env and fill in TYPESAFE_API_KEY from console.typesafe.ai, then npm run dev. The README's structure notes the key exists only in the server-side Vite plugin, never in browser code.
Yes. The README's setup step is putting TYPESAFE_API_KEY into .env, obtained from https://console.typesafe.ai/settings/keys, and the captured README documents no mock mode. Every age and gender guess costs a live API call.
No accuracy figures are published: the README and the digest contain no evaluation numbers, so no claim can be made. The app deliberately surfaces probabilities rather than one answer, and the demo video walks eight example names — inspect those outputs rather than trusting a headline.
Per the README, server/plugin.ts attaches the /api/age endpoint to the Vite dev and preview servers, so the key stays on the server. The React app calls /api/age with country and name and only receives the probability results.
It is a small React project by GitHub user ximhear; the madewithjev build page attributes it to C.H Lee. The GitHub metadata shows no license, so check with the author before reusing the code.
More Jev resources like this
An AI companion that replies only with facial expressions: Jev judges each message and picks one of 16 moods while blobatar morphs its face, with no text replies and no visible chat history.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
appchainai/jevatarTypeScript
appchainai/jevatarTypeScriptA semantic command palette demo where Jev ranks 77 commands by intent in Portuguese or English: one Choice question per keystroke, with the full probability distribution over the command catalog as the ranking. Runs side by side with a classic fuzzy matcher that fails honestly on the same queries.
Jev Demos & Experiments#community#catalog-import#cobanov
Community
amycardoso/jev-paletteJavaScript
amycardoso/jev-paletteJavaScriptA live, graphical dojo for Jev with six real-time canvas scenes over one WebSocket: task routing across model tiers, ticket triage, inbox-scale queues and an honest Jev-vs-Claude gauntlet. Boots in SIM mode without an API key.
Jev Demos & Experiments#community#catalog-import#madewithjev
A Next.js console whose whole design system is generated at runtime by Jev from a one-sentence brief: type 'an 18th century printed book' and every visual decision is chosen, not written, from a catalog a person authored.
Jev Demos & Experiments#community#catalog-import#madewithjev
Community
bilune/jev-designTypeScript
bilune/jev-designTypeScriptJevSpeak explores whether a model that cannot generate text can still talk: about 13 parallel Jev decisions per turn become a typed Semantic IR that a deterministic compiler renders in English or Chinese. Live at jevspeak.org.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
mm-sheng/jevspeakTypeScript
mm-sheng/jevspeakTypeScriptA one-page playground and test bench for TypeSafe Jev: pick a backend, load an example and run typed questions against Jev through OpenRouter or TypeSafe, an LLM baseline, or a keyless mock — all speaking the same /v1/systemone contract, with an inspector for the answer distributions.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
creativoma/here-we-go-jevTypeScript
creativoma/here-we-go-jevTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.