
Introducing our Browser Agent Evals. We benchmark frontier and open models using various harnesses on computer-use tasks. Our evals are fully open source and reproducible via our Evals CLI.
✓the SDK for browser agents, built by @browserbase join the discord: discord.gg/stagehand

Introducing our Browser Agent Evals. We benchmark frontier and open models using various harnesses on computer-use tasks. Our evals are fully open source and reproducible via our Evals CLI.

Everyone wants to build agents, but how do you actually get them ready for production? @joaomdmoura, CEO of CrewAI (@crewAIInc) came to our conference, Navigate 2026, to talk about what he learned from over 2.5 billion agent executions.

Your agent pauses/ crashes mid task. Can a new process pick up where it left off? Stagehand 4.4 adds browser.disconnect() so an agent can detach and leave the browser running and a new agent can reattach to the same browser and can complete the task. This unlocks use cases like human handoffs, scheduled resumes, agent crashes. In the clip, Pi asks for approval, waits 30 minutes, then reconnects and finishes the same checkout.

See our full evaluations here: stagehand.dev/evals

Fable 5.2 scores 92% on HardBench, our curated benchmark of difficult computer-use tasks. It beats the previous champion, Opus 5.5, in accuracy, but costs 2.5x more and is 13.76% slower on average.


The @LangChain team evaluated 7 different Browser Tools to power Managed Deep Agents. It's no surprise that Stagehand was simultaneously the fastest, cheapest, and most accurate. Read the full report to learn how.

Browserbase is now available as a one-click install in the Antigravity Plugin marketplace. Navigate sites, fill out forms, and take screenshots with a verified browser that doesn't get blocked.

Your agents are only as good as their context, and the most valuable context is often locked behind a login. Introducing Authenticated Fetch, 1 request to instantly extract data from logged-in sites. It’s 3x faster than a full browser session, and available on all plans today.


To do real work on your behalf, agents need to sign-in securely. We’re excited to partner with 1Password so your agents can log in without ever seeing your passwords. Agents request a login, you approve it in 1Password, then credentials are sent directly to the browser.

Read the full post: stagehand.dev/blog/pydantic-…

You can extract typed data from any website using @pydantic and Stagehand. Using Pydantic's enforced typing and Stagehand's structured extract, you can build robust and self-healing web scraping pipelines. Read our full blog post below.

Full repo & examples here: github.com/browserbase/opena…

Power your browser agents with Stagehand v4 in OpenAI's official SDKs: docs.stagehand.dev/v4/integr…

New ship on browse.sh - record mode! -> fire up a browser session -> show your agent what to do, click-by-click -> hit export to download your finished workflow you get a SKILL.md your agent can follow, plus scripts for @Stagehanddev, Playwright, or Puppeteer.