User repository on GitHub
Natural-language end-to-end tests for web apps, powered by Jev and Playwright.
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jev E2e
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.
- Stars
- 14
- Language
- TypeScript
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- Jason Lu
- Last verified
- Oct 2026
- Languages
- TypeScript
- Platforms
- CLIPlaywrightOpenRouterBrowser
- Capabilities
- Open sourceRuns locallyRequires API key
Highlights
- In the eBay cart-flow comparison the same written steps took 47 s on Jev versus 79 s on Claude Sonnet 5, shown in a video recorded at 10.77x playback.
- Defaults route control selection to typesafe/jev-1.13 through OpenRouter, with an optional planner for prose and no silent model fallback.
- Playwright verifies expectations independently, and missing evidence or unsupported requirements produce BLOCKED rather than a pass.
- Unchanged flows can replay with zero model calls using saved controls; stale targets are repaired by Jev.
- Runs default to a $0.05 model budget and a 60-second deadline per case, with your own OpenRouter key, auth fixtures and stop controls.
Quickstart
bash
git clone https://github.com/perixtar/jev-e2e.git
npm ci
npm run build
node dist/cli.js setupWatch out
Grounded in the truncated repository README, its linked eBay benchmark notes and GitHub metadata reviewed on 2026-10-15; the project is a local alpha with no npm release, and the README states the eBay comparison is a UI execution experiment that does not measure natural-language planning or the unmodified CLI's reliability.
Questions about this entry
Short answers drawn from the linked project or page.
You describe a flow and what should be true at the end; it turns that into a test plan, uses Jev to select the controls on the page, and runs the test with Playwright. Results are PASS, FAIL or BLOCKED, with an HTML report, JSON and masked screenshots.
Save a case in a .cases file. With --planner on you can describe the flow in prose with a concrete expectation, or skip the planner and use explicit Goal, Step and Expect templates; the README example checks a create-and-persist flow.
The defaults are typesafe/jev-1.13 for control selection and optionally openai/gpt-4.1-mini for interpreting prose, both through one OpenRouter key; there is no silent fallback. Runs default to a $0.05 model budget and a 60-second deadline per case.
A shared human-authored cart flow (search, add two items, change quantity, remove one, refresh and verify) with 31 independent checks across three models. Jev finished in 47 s versus 79 s for Claude Sonnet 5, but it measured UI execution, not planning or the unmodified CLI.
It is alpha and installed from source: clone the repo, npm ci, npm run build, node dist/cli.js setup, then put OPENROUTER_API_KEY in .env. Requires Node.js 22+, and no npm release exists yet.
Yes for repeats: successful flows save their controls and can replay with zero model calls as long as nothing changed, with Jev repairing stale targets. Discovery and prose interpretation are the steps that make paid calls.
A local browser UI started with npm run ui (with npm run demo for the demo site): you point it at a site, review a plan, run it and inspect the evidence. The workbench normally serves on 127.0.0.1:4007 and the demo on 127.0.0.1:4177.
More Jev resources like this
Browser 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-qaTypeScriptAn enterprise admin-console test tool that generates replayable Excel test cases from live browser pages, or replays existing Excel cases, driving Playwright with local Laya or a compatible decision API to match fields, options, and targets.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
anthonyli/laya-pilotJavaScript
anthonyli/laya-pilotJavaScriptA 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.
Jev Tools & CLIs#community#github#testing
Community
neeraj719714/intelliwrightTypeScript
neeraj719714/intelliwrightTypeScriptA 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/sedumTypeScriptLocal-first test selector that asks a judge — classifier.dev by default, or Jev with a TypeSafe key — whether each test could be affected by the current code change, then hands only the selected files to Playwright or Vitest. Uncertainty always runs the full suite.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
baronunread/leanestTypeScript
baronunread/leanestTypeScriptFrom 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.