git404hub

what is uivet fr?

maryanprydatko/uivet — explained in plain English

Analysis updated 2026-05-18

1TypeScriptAudience · developerComplexity · 3/5LicenseSetup · easy

tl;dr

A test and evaluation harness for LLM-generated UI that samples multiple generations, renders them in a real browser, and gates CI on fidelity, accessibility, and layout checks.

vibe map

mindmap
  root((repo))
    What it does
      Samples LLM UI generations
      Renders in headless Chromium
      Gates CI on regressions
    Tech stack
      TypeScript
      Bun
      Playwright Chromium
    Use cases
      Catch inconsistent AI UIs
      Compare models on a leaderboard
      Block bad PRs in CI
    Audience
      Developers
      AI product teams

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

what do people make with this?

VIBE 1

Test whether an LLM reliably renders the same UI correctly across multiple generations.

VIBE 2

Add a CI gate that fails a pull request when generated UI accessibility or fidelity regresses.

VIBE 3

Compare which LLM produces the most accurate and accessible UI using the built-in leaderboard.

what's the stack?

TypeScriptBunPlaywrightChromium

how it stacks up fr

maryanprydatko/uivet0xkinno/neuralvault0xmayurrr/ai-contractauditor
Stars111
LanguageTypeScriptTypeScriptTypeScript
Setup difficultyeasyhardeasy
Complexity3/54/52/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

how do i run it?

Difficulty · easy time til it works · 5min

Offline demo needs no API key, live mode needs a Google or OpenAI API key.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

in plain english

uivet is a testing and evaluation tool built for teams whose product generates user interfaces using a large language model at request time. Normal visual regression tools assume the UI comes from deterministic code, so a fresh render that differs slightly every time defeats them, and normal LLM evaluation frameworks judge text answers rather than the pixels and structure of a rendered interface. uivet is built to sit in that gap: it generates the same scenario several times, renders each version in a real headless Chromium browser, and checks the actual rendered result rather than just the raw text the model produced. For each test scenario, uivet samples multiple generations, checks them against a set of deterministic rules such as fidelity to the required data, accessibility, layout correctness, and console errors, and can also send the render to a multimodal AI judge for a quality score. The results across the samples show how consistent a model's output really is, since one run silently dropping a piece of information, like a price, would otherwise go unnoticed. There is an offline demo mode that replays already-recorded generations with the AI judge turned off, so you can try it in about thirty seconds with no API key and no network calls. A live mode generates fresh UIs using a real model, defaulting to Google's Gemini, though it can also use OpenAI or any OpenAI-compatible server, and this mode does require an API key. uivet is designed to run inside continuous integration as a gate: a failing check or a detected regression against a saved baseline makes the run exit with a failure code, so a pull request that makes UI generation worse can be caught automatically. The project also publishes a public leaderboard comparing how different models perform on the same fixed set of scenarios, using only the deterministic checks with the AI judge turned off, to compare accuracy and accessibility across models. It is not yet published on npm, so it is installed directly from its GitHub repository.

prompts (copy fr)

prompt 1
Walk me through running uivet's offline demo to see fidelity and accessibility checks with no API key.
prompt 2
Help me write a uivet.config.ts scenario that checks a generated dashboard UI against specific JSON data.
prompt 3
Show me how to add uivet as a CI gate in GitHub Actions with a saved baseline for regression detection.

Frequently asked questions

what is uivet fr?

A test and evaluation harness for LLM-generated UI that samples multiple generations, renders them in a real browser, and gates CI on fidelity, accessibility, and layout checks.

What language is uivet written in?

Mainly TypeScript. The stack also includes TypeScript, Bun, Playwright.

What license does uivet use?

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

How hard is uivet to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is uivet for?

Mainly developer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.