
Record mode is now generally available. No prompting or instructions, just show Director how to do it once and it learns to automate it. Try it for yourself at director(dot)ai

what would you like to automate? built by @browserbase

Record mode is now generally available. No prompting or instructions, just show Director how to do it once and it learns to automate it. Try it for yourself at director(dot)ai

The Browserbase dashboard got a makeover. In the last few months we've shipped a ton of new features and improved our dashboard's UI. Here are some of our favorites.

Our Contexts API enables your agents to stay securely authenticated on websites, so they can perform actions in the places you actually work. Contexts are now configurable in the dashboard, and you can filter browser sessions that used a specific Context.


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.

GPT 5.6 Sol absolutely crushes on computer-use. While barely losing to Fable in accuracy, it makes up in speed and cost, being ~3 times faster on average. Grok 4.5 is also had a step change improvement, matching Gemini 3.5 flash in accuracy.

If you didn’t see the Browserbase puppies, you missed out. Last week we took over AIE, teaching the world’s best AI engineers how to build agents that reliably interact with the web. We also launched Agents, a fully managed browser agent you can call with a single API.

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.
Charly Poly @whereischarly May 28 Article How autonomous does your browser agent need to be? When you build a browser agent, one of the first decisions you make is how much of the work the AI should own. Should it follow a script and only reason when needed? Should it own the full loop and


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

Grok Build's traces are pretty cool in the TUI, They auto compact in the UI as well so it doesn't overfill. Here it is using @browserbase Fetch to see what's on the grok marketing website.

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

imagine a world where you never pay the discovery tax twice. (utopia) that's autobrowse. your agent figures out the hard stuff once and every run after that is fast and cheap. if you're new to browser automation, skills, or want your AI to stop forgetting, this is for you.

Browserbase saves @tryramp's customers over 50,000 hours of manual work every year. Together, we co-built Ramp's procurement agent and became the first customer.

The web talks HTML. Agents talk markdown. Fetch API now returns content as markdown or structured JSON from any URL. That means up to 70% fewer tokens to access the whole web, with one API.

Hermes Agent by @NousResearch natively integrates with Browse.sh, Give Hermes any URL and find a skill for it in our catalog, or create your own. Watch it find the NASA picture of the day for me.
This tweet is unavailable