Hi HN! I’m Anirudh — longtime lurker, first time poster, and I couldn’t be more excited to show you Stagehand.<p>Stagehand is a TypeScript project that extends Playwright with three simple AI methods — act, extract, and observe. We’d love for you to try it out using the command below:<p><pre><code> npx create-browser-app --example quickstart
</code></pre>
Here’s a sample workflow:<p><pre><code> const stagehand = new Stagehand();
await stagehand.init();
// Stagehand overrides the Playwright Page and Context classes
const { page, context } = stagehand
await page.goto("instadash.com") // Regular Playwright
// Take action on the page
await page.act({ action: "click on taqueria cazadores" })
// Extract relevant data from the page
const { price } = await page.extract({
instruction: "extract the price of the super burrito",
schema: z.object({
price: z.number()
})
})
</code></pre>
We built Stagehand because we loved building browser automations using Playwright and Selenium, but we grew frustrated at how cumbersome it is to just get started and write simple browser automations. These frameworks, while incredibly powerful, are built for QA testing and are thus notoriously prone to fail if there are minor changes in the UI or underlying DOM structure.<p>The goal of Stagehand is twofold:<p>1. Make browser automations easier to write
2. Make browser automations more resilient to DOM changes.<p>We were super energized by what we’ve been seeing with vision-based computer use agents. We think with a browser, you can provide even richer data by leveraging the information in the DOM + a11y tree in addition to what’s rendered on the page. However, we didn’t want to go so far as to build an agent, since we wanted fine-grained control over each step that an agent can take.<p>Therefore, the happy medium we built was to extend the existing powerful functionalities of Playwright with simple and extensible AI APIs that return the decision-making power back to the developer at each step.<p>Check out our docs: <a href="https://docs.stagehand.dev" rel="nofollow">https://docs.stagehand.dev</a><p>We’d love for you to join and give us feedback on Slack as well: <a href="https://stagehand.dev/slack" rel="nofollow">https://stagehand.dev/slack</a>
This looks awesome.<p>What I would love to see either as something leveraging this, or built in to this, is if you prompt stagehand to extract data from a page, it also returns the xpath elements you'd use to re-scrape the page without having to use an LLM to do that second scraping.<p>So basically, you can scrape new pages never before seen with the non-deterministic LLM tool, and then when you need to rescrape the page again to update content for example, you can use the cheaper old-school scraping method.<p>Not sure how brittle this would be both going from LLM version to xcode version reliably, or how to fallback to the LLM version if your xcode script fails, but overall conceptually, being able to scrape using the smart tools but then building up basically a library of dumb scraping scripts over time would be killer.
This looks very cool and makes a lot of sense, except for the idea that it should take the place of Playwright et al.<p>Personally I'd love to use this as an intermediate workflow for producing deterministic playwright code, but it looks like this is intended for running directly.<p>I don't think I could plausibly argue for using LLMs at runtime in our test suite at work...
This looks really cool, thanks for sharing!<p>I recently tried to implement a workflow automation using similar frameworks that were playwright or puppeteer based. My goal was to log into a bunch of vendor backends and extract values for reporting (no APIs available). What stopped me entirely were websites that implemented an invisible captcha. They can detect a playwright instance by how it interacts with the DOM. Pretty frustrating, but I can totally see this becoming a standard as crawling and scraping is getting out of control.
I've been playing around with Stagehand for a minute now, actually a useful abstraction here. We build scrapers for websites that are pretty adversarial, so having built in proxies and captcha is delightful.<p>Do you guys ever think you'll do a similar abstraction for MCP and computer use more broadly?
Cool! Before building a full test platform for testdriver.ai we made a similar sdk called Goodlooks. It didn't get much traction, but will leave it here for those interested:
<a href="https://github.com/testdriverai/goodlooks">https://github.com/testdriverai/goodlooks</a>
Hey Anirudh, Stagehand looks awesome, congrats. Really love the focus on making browser automations more resilient to DOM changes. The act, extract, and observe methods are super clean.<p>You might want to check out Lightpanda (<a href="https://github.com/lightpanda-io/browser">https://github.com/lightpanda-io/browser</a>). It's an open-source, lightweight headless browser built from scratch for AI and web automation. It's focused on skipping graphical rendering to make it faster and lighter than Chrome headless.
People must be excited for this since a lot of people are commenting for the first time in months or years to say how much they love it. Some people liked it so much they commented for the first time ever to say how great it is.
Looks interesting. I know about the similar project - <a href="https://zerostep.com" rel="nofollow">https://zerostep.com</a>. Is it basically the same?
Does it operate by translating your higher level AI methods into lower level Playwright methods, and if so is it possible to debug the actual methods those methods were translated to?<p>Also is there some level of deterministic behavior here or might every test run result in a different underlying command if your wording isn’t precise enough?
Cool to see another open source AI browser testing project! There’s a couple of others I’ve heard of as well:<p>Skyvern: <a href="https://github.com/Skyvern-AI/skyvern">https://github.com/Skyvern-AI/skyvern</a><p>Shortest: <a href="https://github.com/anti-work/shortest">https://github.com/anti-work/shortest</a><p>I’d love to hear what makes Stagehand different and pros/ cons.<p>Of course, I have no complaints to see more competition and open source work in this space. Keep up the great work!
I’m curious how this compares to playwrights already built in codegen:<p><a href="https://playwright.dev/docs/codegen-intro" rel="nofollow">https://playwright.dev/docs/codegen-intro</a><p>Is a chat bot easier to reiterate a test?
Congratulations. This is super cool.<p>I often thought E2E testing should be done with AI. What I want is that the functionality works (e.g.: login, then start an assignment) without the need to change the test each time the UI changes.