Hey HN! I built E2E Test Agent – a testing framework where you write tests in plain English and AI agents execute them.
Instead of:
await page.locator(“#main-content”).scrollIntoView();
await page.click(‘button[data-testid=”get-started-btn”]’);
You write:
open playwright.dev
scroll all the way down
click on “Get started”
check if the page side menu is visible
This means:
– No more brittle selectors breaking on every refactor
– Non-technical stakeholders can write tests
– Tests survive UI refactors
– Much less maintenance overhead
It works with OpenAI, Claude (via compatible endpoints), or any local LLM that supports the OpenAI API format.
“`
npm install e2e-test-agent
“`
Would love to hear your thoughts! Especially curious about:
– What testing pain points this might solve for you
– Concerns about AI non-determinism in tests
– Ideas for extending it (API testing, database validation, etc.)
GitHub: https://github.com/armannaj/e2e-test-agent
npm: https://www.npmjs.com/package/e2e-test-agent
website: https://e2eagent.io
Comments URL: https://news.ycombinator.com/item?id=45942443
Points: 1
# Comments: 0
Source: github.com
