Show HN: I built E2E Test Agent – describe tests in plain English,AI executes it(github.com)
github.com
Show HN: I built E2E Test Agent – describe tests in plain English,AI executes it
https://github.com/armannaj/e2e-test-agent
1 コメント
hey! cool project, feels very similar to [stagehand](https://github.com/browserbase/stagehand), although stagehand doesn't have much in the way of e2e testing. might be worth building on top of that though since playwright MCP can overwhelm an agent with tool overload
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