Most companies view new model releases as a threat to their existence.
Browserbase only improves as labs release better models.
Our customers get more out of our infrastructure, and stay ahead of the bleeding edge of AI.
Are LLMs actually good enough to fully automate scientific research?
If you're an engineer or researcher, we're hosting a panel with lead researchers from Microsoft and Nvidia on June 16th at the Browserbase office.
Apply to attend below!
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
See how your favorite models perform on our computer use evals,
We found that Opus 4.8 is the most accurate on our eval set, beating out leading models from OpenAI and Gemini.
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.
Picking the wrong API for browser automation makes your system slower, more expensive, and harder to debug.
We wrote a blog explaining how the best AI teams use our Search, Fetch, and Browser APIs effectively.
You can't just give a model the ability to run CDP commands and expect it to perform well in production.
Real browser agents need a harness that provides security, identity, caching, credential brokering, and memory.
Read about how we think about the browser agent harness.
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?
https://t.co/AT3ywxHCjo 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
Today, we're launching 4 official partner skills on https://t.co/ZbU21ECKPE 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