Sabitlenmiş Tweet
Stagehand
426 posts
Stagehand
@Stagehanddev
the SDK for browser agents. 2M monthly downloads & 21k stars, built by @browserbase Join the Discord: https://t.co/Q5Uxzlhr51
chrome devtools Katılım Şubat 2025
41 Takip Edilen4.8K Takipçiler
Stagehand retweetledi
Deep Agents can now access the whole web like humans do.
Equip your Deep Agent with Browserbase's search, fetch and browser subagents for quick web browsing with session replay and detailed traces.
English
Stagehand retweetledi
Stagehand 3.3.0 is live!
What's new:
- Verified mode for improved agent identity
- Adaptive thinking with Anthropic models
- Agent usage now shows up in Stagehand API metrics
- Strict structured outputs for supported models
- Improved file upload elements in page snapshot
English
Stagehand retweetledi
Introducing the /browser-trace skill,
Give your agent 100% observability into its browser: dump network requests, DOM content, screenshots, and CDP logs into a searchable filesystem.
Great for reverse engineering, autoresearch loops, and monitoring the situation ™️.
English
Stagehand retweetledi
Stagehand retweetledi
The standard verifier for computer use agents is wrong 45% of the time. We got ours to 1%.
We ran 96 experiments with Microsoft's FARA team to build the Universal Verifier, an architecture for grading computer use trajectories that matches human inter-annotator agreement. 🧵
Miguel@miguel_gonzf
English
Stagehand retweetledi
I built an AI-powered ice cream finder because Google search results are unusable and I deserve better.
Powered by 2 new @browserbase APIs. Under 20 min to build. Zero regrets. 🍦
English
Stagehand retweetledi
Stagehand retweetledi
Hermes agent supports Browserbase to browse and interact the web just like a human.
You can add it when you setup your agent, or add it with browserbase.com/SKILL.md
Watch it add deodorant to my amazon cart, something much needed for engineers around the world.
English
See more about what we're building:
browserbase.run/platform-blog
English
Stagehand is the SDK for browser agents.
Build, run, and deploy them on the Browserbase Platform for best in class observability and now a Model Gateway.
Paul Klein IV@pk_iv
Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.
English
Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online.
Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people.
With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway.
Stop waiting on integrations, build agents that can browse and interact with the web just like humans.
English
You've never felt true dopamine unless you've had your OSS repo get 1k GH stars. With Stagehand we've done it 21 times.
We're hiring devs who want to turn that feeling into their full‑time job.
If you love building dev tools and tinkering with with agents / LLMs or browser automation, we want to talk!
English
Stagehand retweetledi
Introducing /ui-test
Give your agent a PR, and it'll test your feature in a real browser, generating an HTML report with UI fixes
The planner agent generates adversarial test cases to break your app, assigns them to subagents, and evaluates the page using the @browserbase CLI
We reviewed a merged PR on @calcom and found a bunch of small UI nits:
English