Introducing Stagehand v4: the SDK for browser agents.
Playwright was built for testing, we built Stagehand for your agent: with improved context management, self-healing actions, and iframe support.
We got early access to Fable 5.1 and evaluated it extensively across our internal benchmarks.
It outperformed all other frontier models (including Fable 5) on accuracy scoring 92.11%, while being 60% cheaper than Fable 5 per task.
Create agent-ready web apps for the WebMCP Challenge → goo.gle/4qpDQYV
We're excited to see ChatGPT supporting WebMCP, the experimental standard that lets users and AI agents navigate websites together. In the @OpenAIDevs WebMCP Challenge you can experiment with it and
Stagehand v4 gives you more control over how your browser actions are cached.
With Browserbase caching, your scripts automatically run up to 80% faster.
Introducing Stagehand v4: the SDK for browser agents.
Playwright was built for testing, we built Stagehand for your agent: with improved context management, self-healing actions, and iframe support.
Last week we launched Stagehand v4, the fastest and most token efficient way to control a browser.
We benchmarked it extensively and found that Stagehand repeatedly outperforms Playwright in every action and in every region on Browserbase.
Introducing Stagehand v4: the SDK for browser agents.
Playwright was built for testing, we built Stagehand for your agent: with improved context management, self-healing actions, and iframe support.
