We’re graduating from Playwright. We’re grateful it gave devs the foundation to build fast and adopt even faster, but fit changed as we scaled. Stagehand’s next chapter goes deeper into the browser stack.

Find out why & where we're headed next in our blog👇 https://t.co/8yeAYudMfV

Drop the "hq", it's cleaner. We're now @browserbase

Director can now generate python code snippets, Get your Stagehand scripts in python with a few clicks. Try it out in director(.)ai. 🐍

Not all invoices get ingested. Director searches through email and forwards receipts to @tryramp, Time is money, save even more with Director.

This is one of the biggest bets I've made as a founder. Today we're launching Director 2.0: a free app that enables anyone to automate web tasks with a single prompt. Powered by Browserbase and Stagehand. It's #2 on Product Hunt now - help us get #1: https://t.co/PEr0I7ba7t

The only fall activity you should be doing is locking in. Pre-book all your 6AM’s without worrying about disappearing slots, Making PRs in the gym and GitHub.

Not only is this new Claude Model very accurate, It's also much faster & cheaper than other @AnthropicAI models, at ~2 cents per task & 4.73s average task time.

Micromanaging your macros? Authenticate with 1password without exposing credentials, Autofilled directly from your vault.

Now that sf summer is over… it’s bulk szn But I hate having to log into Forkable every day to pick meals So I used @trydirector to hit my macros for me. Agentic autofill w/ 1password authenticates without exposing my credentials Preordering those gains

Official Docs: https://t.co/3hrw2FhFmH

Get started with the evals CLI by cloning the stagehand repo. (leave a Star while you're there!) https://t.co/HrR4wuybLK

Everyone says their models/product is the best, and use their own custom benchmarks as proof. We believe all benchmarks should be Open Source, and you should be able to see the results for yourself. That's why we built the Stagehand Evals CLI. Run computer use evaluations &

If you’re designing repeatable workflows with @Stagehanddev Chances are you’re doing it wrong. 80% of our users could improve their automations by just doing this one thing. Hear me out 🧵

Finding housing in SF shouldn’t be a full-time job. Director agents browse listings, filter by your criteria, and compile a clean CSV. Automate your apartment hunt.

Over 90% of YC companies end up failing So I built an app to predict if they will become a unicorn or not. Try it out, link below.

i love open source! @Stagehanddev is the #1 trending github repository in the world today. so proud of this team and community behind the project!

Here is an example on how to build a local browser agent using the new Gemini 2.5 Computer use model and @browserbasehq stagehand! Stagehand extends Playwright by adding AI-powered primitives for browser automation. - act: Executes actions using natural language commands. -

Find all the templates here: https://t.co/q6crmp7UE7

Try out the NEW Gemini computer use model with Stagehand! Copy the command to get started today. npx create-browser-app --template gemini-cua