bug0inc

bug0inc / passmark

Public

The open-source AI framework for regression testing

passmark.dev ai ai-agents aigateway aisdk playwright
10
0
100% credibility
Found Mar 31, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Passmark is an open-source framework that enables writing and running web tests in natural language using AI to execute steps and verify results automatically.

How It Works

1
🔍 Discover Passmark

You hear about Passmark while searching for a simple way to automatically check if your website still works after changes.

2
📦 Set up your test space

You create a cozy folder for your tests, just like starting a new notebook for notes.

3
🤖 Link smart AI helpers

You connect a couple of clever AI friends from trusted places so they can understand and act on your instructions.

4
✏️ Write tests in plain words

You list simple steps like 'go to the shop, pick a shirt, add to basket' – no fancy code needed.

5
▶️ Launch the test

With one click, your AI buddies follow your list, click around, and check everything works perfectly.

✅ See the magic report

You get a friendly summary showing what passed, what broke, and smart explanations – now your site stays bug-free forever.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is passmark?

Passmark is an open-source AI framework for regression testing built in TypeScript that integrates with Playwright. It lets you write E2E tests using natural language steps—like "Add product to cart"—which AI models execute via browser automation, complete with assertions like "Cart shows the item." Unlike one-off PR checks, it focuses on continuous regression testing with Redis caching for speed, auto-healing on failures, and multi-model consensus from Claude and Gemini to verify outcomes reliably.

Why is it gaining traction?

This ai agents framework open source stands out with smart caching that replays fast Playwright actions on repeats, slashing AI costs and latency after the first run. Features like dynamic placeholders for emails/OTPs, pluggable email extraction, and single-call user flows make tests data-driven without brittle selectors. As a github open source tools entry, it routes through Vercel AI Gateway or direct providers, appealing to devs seeking an llm open source framework beyond basic screenshot diffs.

Who should use this?

Playwright users maintaining flaky E2E suites for e-commerce checkouts, auth flows, or forms with emails. QA engineers or full-stack devs at startups testing regressions daily without constant prompt tweaks. Teams evaluating open-source frameworks like this passmark benchmark alternative to proprietary AI testers.

Verdict

Promising open-source framework for AI-powered Playwright tests, but with 10 stars and 1.0% credibility score, it's early—docs are solid, quickstart works, but watch for Playwright API stability. Try in non-critical CI for caching wins; contribute if you need production polish.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.