User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Demos & Experiments
Jevchat — kt3k
A ChatGPT-style chat UI for Jev where answers are decisions, not prose. Pick Yes/No or styles like Yes/No/Maybe, Pirate or Tabloid, and expand any reply to see Jev's calibrated probability for every option. Runs on Deno.
- Stars
- 1
- Language
- JavaScript
- Reading time
- 2 min
- Published by
- Community
- Author
- kt3k
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jevchat — kyle-pena-nlp.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- JavaScriptTypeScript
- Platforms
- Browser
- Capabilities
- Open sourceSelf-hostedRequires API key
Highlights
- The server proxies POST /api/chat to POST https://api.typesafe.ai/v1/systemone, so the API key never reaches the browser.
- Every answer style sends a choice question whose criteria are the style's answers, so Jev itself picks the reply; details show each option's probability.
- Remix styles (Daily fortune, Politician, Tabloid) cross question fragments with verdict templates, and Jev picks one fully composed answer in a single choice.
- Chat titles come from a second choice question over Intl.Segmenter fragments of the first message, with playful fallbacks when Jev is not confident.
- English and Japanese UI default to the browser language; history is capped at 10 chats in localStorage — the README calls it a demo.
Quickstart
bash
JEV_KEY=your-api-key deno task startWatch out
Copy reviewed against the full README on 2026-10-15; GitHub metadata lists no license for the repository. History is limited to 10 chats and lives in localStorage, so the project frames itself as a demo rather than a production client.
Questions about this entry
Short answers drawn from the linked project or page.
A ChatGPT-style chat UI for Jev, TypeSafe's System One model that never generates text — it only decides. It has a sidebar with chat history and a main chat area, and a hosted copy runs at jevchat.kt3k.deno.net.
By default Jev answers Yes or No. You can switch to Yes/No/Maybe, Mom, Pirate, Tabloid headlines and other sets, or create your own custom set of answers for Jev to choose from; custom styles are stored locally.
The server proxies POST /api/chat to POST https://api.typesafe.ai/v1/systemone, so the API key never reaches the browser. Every answer style sends a choice question whose criteria are the style's answers, and the details toggle shows the calibrated probability for every option.
Remix styles split your question into fragments with Intl.Segmenter and cross them with verdict templates like 【悲報】{}、ナシ, so Jev picks one composed answer. A second choice question over fragments names the chat, with playful fallbacks when Jev is not confident.
It needs Deno 2.x and a TypeSafe AI API key. Run JEV_KEY=your-api-key deno task start and open http://localhost:8000.
Set the JEV_KEY environment variable in your Deno Deploy project settings and run deno deploy; the entrypoint is main.ts. The key stays server-side in both the local and deployed setups.
History is kept in localStorage with a maximum of 10 chats — the README calls it a demo. GitHub metadata also lists no license for the repository.
More Jev resources like this
JevSpeak 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/jevspeakTypeScriptAn 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 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-jevTypeScriptA BYOK workbench for practicing Jev concepts without official access: emulates State, Noul, Score and Choice via Groq, OpenAI, Anthropic, Gemini or local Ollama, or runs against native Jev with authorized credentials.
Jev Demos & Experiments#community#catalog-import#logicrw
A 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-paletteJavaScriptVercel Labs example that routes three forms by context with Jev and AI SDK: Jev's team choice is accepted when its confidence is at least 95%, otherwise openai/gpt-6-luna-fast independently evaluates the submission and its choice becomes final.
Jev Demos & Experiments#community#catalog-import#logicrw
From 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.