User repository on GitHub
Use Jev to make art!
- Forks
- 7
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jevinci
A small local app that turns Jev's per-pixel probability distributions into paintings: stroke pigments are sampled from the probabilities, mean color supplies the underpainting, and entropy controls relief, rendered in a browser worker.
- Stars
- 63
- Language
- JavaScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- achimala
- Last verified
- Oct 2026
Works forJev for Scoring
- Languages
- JavaScriptPython
- Platforms
- Browser
- Capabilities
- Open sourceRuns locallyRequires API key
Highlights
- Runs with python3 server.py; the loopback helper serves files and forwards requests to the fixed Jev endpoint because the API disallows browser CORS origins.
- Question construction, batching, probability processing, and painting all run in the browser; rendering happens in a module worker at 560x560.
- One algorithm handles palette, HSL, binary RGB, and silhouettes; HSL and RGB channels assume independence because Jev supplies no joint distribution.
- Strokes follow local luminance contours and a height map supplies impasto lighting; the finished textured painting fades in over 550 ms.
- Paintings join an in-memory carousel and clear on reload; the API key is stored unencrypted in this browser's localStorage.
Quickstart
bash
python3 server.py
node --test tests/jev.test.mjs
python3 -B -m unittest discover -s tests -p 'test_*.py'Watch out
README reviewed 2026-10-15; the app calls itself a local creative experiment, not a publicly hosted multi-user service, and says the output is an artistic transformation rather than a lossless probability chart. Model requests cost tokens and larger grids make more requests, and no accuracy or quality metrics are published.
Questions about this entry
Short answers drawn from the linked project or page.
A small local app that turns Jev's pixel probability distributions into paintings: you choose a representation and grid size, enter a prompt, and each finished painting joins an in-memory carousel.
It asks Jev about each pixel of a grid and turns the returned probability distributions into painting decisions: spatially correlated categorical sampling supplies stroke pigments, mean color supplies the underpainting, and entropy controls relief.
Run python3 server.py, open http://127.0.0.1:8791, open Settings, and paste your Jev API key. Use --port if the default port is taken, and stop the helper with Ctrl+C when you are done.
A representation of palette, HSL, binary RGB, or silhouettes, a grid size, and a prompt. The same rendering algorithm handles all of the representations, and paintings are cleared when you reload the page.
Python 3.9 or newer and a modern browser with module workers and OffscreenCanvas; no packages, build step, or Node installation, and no environment variables are required. Generation uses your TypeSafe account.
The key is saved in this browser's localStorage for this origin and is not encrypted; clear the key field to forget it. Prompts and keys go only to TypeSafe, and model requests cost tokens with larger grids making more requests.
It is an artistic transformation, not a lossless probability chart; HSL and RGB channels assume independence, paintings clear on reload, network and model time is separate from rendering time, and it is not a publicly hosted multi-user service.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Text-to-screenshot (Malay Vasa)
X: Google's MediaPipe Decision Maker, tested in the browser
X: Playwright CLI + Jev vs Playwright MCP
X: jev-ultrafast splits every browser decision into operation, target and value. JEV passed 18,000 stars in its…
More Jev resources like this
A 25-second IT-buzzword typing game built to feel how fast and cheap Jev is: each word gets five typed judgments in one request, and the screen shows the running cost next to the real HTTP request and response.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
pochang6/jev-buzzword-rushJavaScript
pochang6/jev-buzzword-rushJavaScriptBrowser-only Laya demo suite: four Vite apps — a Traditional Chinese decision playground, Gomoku, Big Two and a 3D maze — run the Laya ONNX model on-device through Transformers.js, downloading fp16 weights from Hugging Face on first use.
Jev Demos & Experiments#community#catalog-import#madewithjev
Community
killkli/open-jev-layaPython
killkli/open-jev-layaPythonA local app that reads a few lines of notes about your product and lets Jev pick its way to a finished landing page: Jev never writes text, it only chooses between options, and code builds the page from those picks.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
sagapranav/jev-pagesHTML
sagapranav/jev-pagesHTMLA workshop of small, inspectable Python experiments for TypeSafe System One models: ten critical bays, from fraud screening to emergency dispatch, each giving Jev a realistic state while deterministic policy keeps authority over the next action.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
jgalego/jevs-garagePython
jgalego/jevs-garagePythonA playable Three.js driving simulator where Jev-powered autopilot picks steering and speed up to four times per second: compact tables of eligible paths, traffic and road boundaries go to Jev while geometry and control math stay local.
Jev Demos & Experiments#community#catalog-import#cobanov
Community
standardagents/jevpilotJavaScript
standardagents/jevpilotJavaScriptAn open-source browser 3D character split between two models: GPT-Live-1 talks with you over WebRTC while Jev reads the live transcript and picks Annie's face, gestures and body language in about 120 ms, with code gates on every answer.
Jev Demos & Experiments#community#github#python
Community
rehan-remade/open-anniePython
rehan-remade/open-anniePythonFrom 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.