User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Intelliwright
A Playwright-based end-to-end test runner for web apps where Jev powers plain-English assertions, actions by description, goal-driven runs and failure triage. Its API mirrors Playwright Test, with test, expect, fixtures and page objects, and every Jev feature is optional.
- Stars
- 3
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- neeraj719714
- Last verified
- Oct 2026
- Languages
- TypeScript
- Platforms
- PlaywrightCLIBrowser
- Capabilities
- Open sourceRequires API key
Highlights
- Jev answers typed questions about the page using the URL, the title and Playwright's ARIA snapshot; it never receives a screenshot.
- Plain-English assertions pass at ai.minProbability, 0.7 by default; actions by description cache as ordinary Playwright locators until the page changes.
- The API mirrors Playwright Test: test, expect, test.describe, hooks and fixtures, with page objects via BasePage and test.extend().
- Failure triage labels every final failure regression, test_bug, flaky or environment in the terminal and the HTML report.
- Providers: TypeSafe, Vercel AI Gateway, OpenRouter or Cloudflare Workers AI; tests that do not use Jev run without a key.
Quickstart
ts
import { expect, test } from "./fixtures";
test("a user can save a note", async ({ page, newNotePage }) => {
await newNotePage.goto();
await newNotePage.save("Groceries");
await expect(page.getByRole("heading", { name: "Groceries" })).toBeVisible();
await expect(page).toSatisfy("the new note is shown with its title");
});Watch out
README and GitHub metadata reviewed 2026-10-17; the README publishes no accuracy numbers for the meaning-based assertions and actions, and Jev features require a provider key while plain Playwright-compatible tests do not.
Questions about this entry
Short answers drawn from the linked project or page.
An end-to-end test runner for web apps built on Playwright, where Jev, TypeSafe AI's decision model, powers plain-English checks, actions by description, goal-driven runs and failure triage. Tests use page objects and an API that mirrors Playwright Test.
Four optional features: assertions check meaning rather than exact text, actions find elements from a description, goal-driven runs work towards a goal one click or fill at a time, and failure triage labels each failure. Every Jev answer is a probability.
Run npm install --save-dev intelliwright, then npx intelliwright init and npx intelliwright install. init never overwrites files or writes an API key; put a Jev key in .env.local next to the config and keep that file out of git.
TypeSafe (TYPESAFE_API_KEY, default model jev-latest), Vercel AI Gateway, OpenRouter and Cloudflare Workers AI. Without ai.provider it uses the first provider whose key is set, and it also accepts any System One compatible host, your own evaluate function or a local mock.
The URL, the title and Playwright's ARIA snapshot of the page, never a screenshot. Password fields are always masked, and ai.redact masks anything else you name.
It keeps the familiar API but adds page objects by default, a test runner with parallel workers, retries, UI mode, HTML and JUnit reports, one sign-in per run with test.auth(), and the optional Jev features layered on top.
Node.js 22 or newer and a web app reachable over HTTP. Cached AI actions skip Jev until the page changes, and the README documents no accuracy evaluation of the AI checks beyond that caching design.
More Jev resources like this
Write end-to-end tests for web apps in plain English; jev-e2e turns each case into a plan, has Jev pick the page controls, and runs it with Playwright, returning PASS, FAIL or BLOCKED with HTML, JSON and masked screenshot evidence.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
perixtar/jev-e2eTypeScript
perixtar/jev-e2eTypeScriptBrowser QA where Playwright drives and films, and Jev judges: natural-language assertions, self-healing locators and goal-driven click loops, with a JSON-flow CLI for agents, a local dashboard and an agent skill.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
jonymusky/jev-browser-qaTypeScript
jonymusky/jev-browser-qaTypeScriptA CLI browser automation tool with optional Jev semantic mode: Surf observes, Jev selects the next action, Surf validates and acts, Jev checks the goal.
Jev Tools & CLIs#community#browser#cli
Community
nicobailon/surf-cliTypeScript
nicobailon/surf-cliTypeScriptA source-available visual UI testing agent in Go: point it at a URL, describe the test, and a six-stage pipeline drives a real Playwright browser while Jev optionally validates requests, picks DOM targets and checks outcomes, falling back to an LLM below 0.9 confidence.
Jev Tools & CLIs#community#github#go
Community
ownweights/argusGo
ownweights/argusGoOpen-source, pre-alpha CLI that runs plain-English browser tests on Playwright, using Jev for bounded decisions: resolving each step, picking elements among offered candidates and judging verify claims with probabilities. Bring your own TypeSafe key; MIT licensed.
Jev Tools & CLIs#community#e2e-testing#playwright
Community
sedum-dev/sedumTypeScript
sedum-dev/sedumTypeScriptA Node CLI for goal-driven web E2E testing: Jev picks the next step from a bounded, code-generated action space, playwright-cli executes it in a real browser, and your test code owns the deterministic assertions, thresholds and final verdict.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
dingw530/playwright-jevJavaScript
dingw530/playwright-jevJavaScriptFrom 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.