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.
CommunityJev Tools & CLIs
Jev Paint
Local MIT-licensed experiment that turns pixel probability distributions from a decision model into paintings, with question building, batching and rendering done in the browser.
- Stars
- 63
- Language
- JavaScript
- License
- MIT
- Published by
- Community
- Author
- achimala
- Last verified
- Oct 2026
About this project
A small local app that turns Jev's pixel probability distributions into paintings. Requires Python 3.9+ and a modern browser with module workers and OffscreenCanvas (current Chrome, Edge, Firefox, or Safari). No packages, build step, or Node installation needed.
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- JavaScript
Highlights
- Palette, HSL, binary RGB and silhouette representations share one deterministic algorithm, so a prompt renders reproducibly.
- Channel probabilities are combined assuming independence because the API supplies no joint distribution; the README calls it an artistic transformation.
- A Python standard-library shim only forwards requests because the API disallows browser origins; it binds loopback and logs nothing.
- Painting runs off the main thread at 560×560, and recorded fixtures let the tests and benchmark run offline at no API cost.
Watch out
Your API key is stored unencrypted in localStorage for the helper's origin, so treat the machine as trusted and clear the field to remove it; changing the port or using localhost gives you a separate storage origin. Generation spends tokens on your own account, larger grids mean more requests, rendering time is independent of model and network latency, and paintings disappear on reload. The README is explicit that the output is an artistic transformation rather than a lossless probability chart, because channel probabilities are combined under an independence the API does not provide. 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.
No. Python 3.9 and a current Chrome, Edge, Firefox or Safari are enough. The browser code is plain ES modules with no runtime dependencies and the helper uses only the standard library, so run the server script and open the loopback address.
In this browser's localStorage for that origin, unencrypted. The helper holds it only while forwarding a request, binds loopback only, checks the request origin, and neither stores nor logs keys or prompts; those go only to the decision endpoint.
No, and the README says so itself. HSL and RGB channel probabilities are combined assuming independence because the API returns no joint distribution, so read a painting as one deterministic artistic rendering rather than a chart you can pull values from.
Rendering does not: four recorded probability fixtures let the tests and benchmark run offline with no API calls. Generating a new painting does, through your own account, and a larger grid means more requests, so start small.
Four: palette, HSL, binary RGB and silhouettes, all handled by one deterministic algorithm so a prompt renders reproducibly. Spatially correlated categorical sampling supplies stroke pigments, mean color supplies the underpainting and entropy controls relief, with strokes following local luminance contours and a height map supplying impasto lighting. Painting runs in a module worker at 560 by 560 and fades in over 550 ms, so rendering time is independent of model and network latency.
Because the API currently disallows browser CORS origins. All question construction, batching, probability processing and painting run in the browser, while a Python standard-library script serves the files and forwards requests to the fixed Jev endpoint. It binds only to loopback, checks the request origin, and neither stores nor logs keys or prompts; no environment variables are required, Ctrl+C stops it, and --port moves it off 8791.
MIT, and independent of TypeSafe: Jev is a TypeSafe service and this project needs your own API access. The pieces are server.py for static files and fixed-destination forwarding, web/jev.mjs for typed questions and four concurrent batches, web/art.mjs for the probability representations, web/renderer.mjs for the deterministic painting algorithm, web/paint-worker.mjs for off-main-thread rendering, and web/app.mjs with index.html and style.css for the gallery.
More Jev resources like this
165GitHub stars
An unofficial changelog for Earth that renders recent reporting as game patch notes. A scheduled GitHub Actions job collects stories, Groq picks headlines for worldwide relevance and writes the patch titles, and the result is committed as saved editions the site, API and RSS read.
Jev Tools & CLIs#community#jevbest
Community
byalex33/changelog.earthJavaScript
byalex33/changelog.earthJavaScript86GitHub stars
Open-source workbench for quant research, office work and futures execution, where a JEV workspace watches markets through TypeSafe Jev against simulation accounts.
Jev Tools & CLIs#community#jevbest
Community
quantskills/QuantStudioJavaScript
quantskills/QuantStudioJavaScript46GitHub stars
Browser app for systematic-review extraction that opens a trial report with supplements and returns verbatim quotes with file and place, stored locally as projects holding studies.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
choxos/jev-reviewerJavaScript
choxos/jev-reviewerJavaScript23GitHub stars
Self-hosted Google Apps Script that classifies Gmail by meaning with Jev Choice over your own dozen-label taxonomy, checking metadata first and full content only when confidence demands it.
Jev Tools & CLIs#community#jevbest#catalog-import
26GitHub stars
Open-source browser extension filtering feed posts by local keywords and, with your own model key, labeling ads, chosen topics, and likely AI-generated share directly on the page.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
pengchujin/ad-radarJavaScript
pengchujin/ad-radarJavaScript2GitHub stars
Chrome extension that labels Bluesky posts and drafts with tone classifiers as you read or type, hiding results the model is not confident about.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
sriganesh/jevibe-checkJavaScript
sriganesh/jevibe-checkJavaScriptFrom the Jev guides
Original write-ups on what this entry is for.
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
From the Jev community
Posts from builders shipping with Jev right now.