Gemini 3.5 Flash + CUA is impressive: on our benchmarks, it performs similarly to frontier models while being on average ~80% cheaper.
It's a reliable model for powering browser agents that balance speed and accuracy on real-world tasks.
WebMCP support is live in Stagehand 3.6 🤘
Websites can now expose typed, first-party tools directly to your agent — Stagehand calls them instead of inferring from the DOM.
Plus: Azure OpenAI auth & smarter act caching.
nobody's adopting WebMCP because site owners have to write and maintain them.
we taught browser agents to do it. webmcp-gen explores any page → generates the spec → stagehand injects and runs it.
here it is finding cheap flights on google flights:
Excited to partner with Anthropic on Managed Agents,
The Browse CLI gives your agents reliable access to the web for advanced tasks.
Read the full documentation below.
New from Code with Claude Tokyo: scheduled deployments and environment variables in vaults are in public beta in Claude Managed Agents, and dynamic workflows in Claude Code are generally available.
Agents now run on a schedule, use your tools securely, and take on bigger jobs.
Claude Fable 5's computer use blows other foundation models out of the water.
On our custom task set it scores 7.3% higher than 4.8 while also being more cost efficient than sonnet 4.5.
Our hybrid agent built into Stagehand significantly outperformed the native CUA harness.
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.
Your agents shouldn't relearn how to use sites every time they visit.
Browse.sh is the web skills catalog for your agents. Since launching 2 weeks ago the community contributed over 300 skills and 35,000+ CLI downloads.
We're 2nd on Product Hunt, help us win product of the day!
Stagehand just crossed 1 Million weekly downloads, but we're not done yet.
New in our latest 3.5.0 release:
- native clipboard API
- screenshots in extract()
- better snapshots & local mode use
Introducing the new Stagehand Evals,
We've been working closely with labs evaluating their latest models on custom tasks that represent real, production use cases.
Excited to push forward the frontier and ensure our customers use the model best for them.
Building Browser Agents has never been easier.
Join us this Thursday (6/4) for an Opus 4.8 webinar with @AnthropicAI and @Letta_AI.
We'll discuss how we evaluate model capabilities with Stagehand and show a live demo on how to power your own agentic products with Browserbase.
The best Browser Agents are built with the right permissions.
We've deployed production agents with companies like Ramp, Lovable, and Clay, each with different levels of autonomy.
Read about how we think about guardrails and autonomy in browser agents.
tired of writing brittle scripts and maintaining CSS selectors just to scrape a site?
browse.sh skills are one-line installs that teach your agent how to navigate any site. DOM patterns, login flows, extraction logic, etc
this whole setup took 30 seconds 👇
Claude Opus 4.8 is the strongest computer-use and browser-agent model we've tested, scoring 84% on Online-Mind2Web.
It's now available via Stagehand's agent mode.
Try it out today → npx create-browser-app
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.
Available today at the same price.
Today, we're launching 4 official partner skills on Browse.sh to improve agent capabilities:
- Get an inbox with @agentmail
- Make any payment with the @link CLI
- Deep research people & companies with @ExaAILabs
- Analyze product insights with @Amplitude_HQ
Excited to announce that we've been named to @Redpoint's InfraRed 100, for the second year in a row.
We're hiring for several roles across engineering, design, and GTM, join us!
We're proud to be among the most impactful and fastest-growing private infrastructure companies within the InfraRed 100 list! 🅱️🔥
The most "mid" company in the space will only go up from here
16 Followers 867 FollowingChief of Staff at String; we give the internet to you // on a mission to build great things in all aspects of life // ex-Bain
228 Followers 7K FollowingConstruyo en semanas productos, automatizaciones y software con IA, para convertir ideas ambiciosas en sistemas reales que mueven negocios. @voltiastudio
3K Followers 5K Following20 years of shipping code to production. AI Engineer
Consulting: https://t.co/c3arbSqD4h
📲 https://t.co/TYFwKehg9A
📮https://t.co/vZ0m38sol7