Stagehand
Dev tools
browser automation framework
SHOW HN2025
How HN took it
12 positive, 15 neutral or asking, 1 mixed, 7 critical, out of 35 comments about the project. Thread score +0.17.
Idea: 11 for, 1 againstPricing: 0 for, 2 againstExecution: 0 for, 1 againstDesign: 0 for, 1 againstPerformance: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Useful abstraction, delightful built-in proxies and captcha handling
From 1 comment
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…
sparab18 on HN
Clean act, extract, and observe methods
From 1 comment
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…
fbouvier on HN
Fast product velocity
From 1 comment
Have been on the Slack for a while and this crew has had an insane product velocity. Excited to see where it goes!
zanesabbagh on HN
Objections
Playwright is built for testing, so extending it for scraping is a poor fit
From 2 comments
It seems to me like Selenium would have been a more appropriate API to extend from, then. Playwright, despite whatever people want it to be otherwise, is explicitly positioned…
andrewmcwatters on HNThat's the same reason everyone else ignores the fact that it's a testing library. Except now you're forcing users to write kludges that wrap around the testing interface.
andrewmcwatters on HN
Runtime LLM calls are expensive and hard to justify per run
From 2 comments
How do you avoid this becoming horrendously expensive per run? Are the results cached if the DOM doesn't change?
kevmo314 on HNThat seems like a pretty tough sell over bare playwright. Unless the UI is constantly changing, the cost of verifying tests are still successful seems like it would eclipse the…
kevmo314 on HN
LLM at runtime makes tests less deterministic
From 2 comments
This looks very cool and makes a lot of sense, except for the idea that it should take the place of Playwright et al. Personally I'd love to use this as an intermediate workflow…
mpalmer on HN> Treating UI test code as some kind of static source of truth is the biggest nightmare in all of UI front end development. Web UIs naturally have a ton of "jank" that…
mpalmer on HN
Requests
Cache extract results so the LLM runs only when page content changes
From 2 comments
This looks awesome. 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…
dchuk on HNCache the response for a given query-page hash pair maybe? So the LLM will only be consulted when the page content hash changes, the previous answer be reused otherwise
9dev on HN
Return XPath selectors from extract for later deterministic scraping
From 1 comment
This looks awesome. 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…
dchuk on HN
Browser extension version
From 1 comment
Any attempt on doing something similar but as a browser extension?
owebmaster on HN
Support for Ollama local models
From 1 comment
Can it be adapted to use ollama? Seems like a good tool to setup locally as a navigation tool.
pryelluw on HN
Questions
How does it handle bot detection and captchas
From 2 comments
How do you get by when every major sites starts blocking headless browsers? A good example right now is Zillow, but I foresee a world where big chunks of the internet are behind…
cjonas on HNThis looks really cool, thanks for sharing! I recently tried to implement a workflow automation using similar frameworks that were playwright or puppeteer based. My goal was to…
asar on HN
How it compares to Playwright codegen
From 1 comment
I’m curious how this compares to playwrights already built in codegen: https://playwright.dev/docs/codegen-intro Is a chat bot easier to reiterate a test?
righthand on HN
Can it automate an existing open browser tab
From 1 comment
Does this open up the possibility of automating an existing open browser tab? (Instead of a headless or specifically opened instance of chrome?)
bluelightning2k on HN
Alternatives named
Skyvern
From 1 comment
Cool to see another open source AI browser testing project! There’s a couple of others I’ve heard of as well: Skyvern: https://github.com/Skyvern-AI/skyvern Shortest:…
jameslk on HN
Shortest
From 1 comment
Cool to see another open source AI browser testing project! There’s a couple of others I’ve heard of as well: Skyvern: https://github.com/Skyvern-AI/skyvern Shortest:…
jameslk on HN
Octomind
From 1 comment
Hi! Kosta from Octomind here. We built basically this: Let an LLM agent take a look at your web page and generate the playwright code to test it. Running the test is just running…
Kostarrr on HN
ZeroStep
From 1 comment
Looks interesting. I know about the similar project - https://zerostep.com. Is it basically the same?
vitalets on HN
Crawlspace
From 1 comment
Thanks so much! Crawlspace is pretty sick too, as is Integuru. A lot of people have different takes here on the level of automation to leave up to the user. As a developer…
hackgician on HN