Outset Capital

@medra_ai Huge! Congrats @medra_ai and @michellearning

@danlovesproofs Very exciting! @danlovesproofs

We built a bug finder. We're finding serious, "let's fix that right now" issues in every codebase we run it on. Introducing Detail!

The future of software is software doing work on your behalf Watch @pk_iv demo how @browserbase makes that possible — with open-source framework Stagehand, managed platform and now no-code builder Director 2.0 Already powering 1000s of apps like Perplexity, Clay and Vercel

@olvrgln Very exciting!

Introducing Mesa, the world’s first multi-agent code review system that truly understands your system and architecture to deliver senior-level reviews.

day in the life at the @browserbase office

Hedra Halloween is on! 🔥 Hailuo 2.3 is now live in Hedra, and it’s time to turn up the heat. We’re giving 1,000 free credits to everyone who makes Halloween content in Hedra and tags it with “Hedra Halloween” — all through Halloween week. Follow + RT + Reply “Hedra Halloween” = the prompt guide into your DM. Make something spooky. Post it. Get featured.

With this release, Stagehand is hands down the best browser automation framework. It’s fast, reliable, efficient, and optimized for AI. Watch the video below to see how we did it:

Super proud of @nikhi1rao @awlk99 @getreflex on the release of Reflex Build From prompt to production — all in pure Python 30% of the Fortune 500 already use Reflex for internal tools Now with Reflex Build they can kick their Python development into warp speed

Blown away by the exceptional talent coming out of @speedrun SR005!! Congrats to the entire a16z speedrun team and the 61 incredible teams that demo'd today.

Sculptor: the missing UI for Claude Code 🎨 Imagine running 5 Claudes in parallel, safely in containers, while you stay in flow. Then bring their work straight into your IDE to test/edit together. This is how one developer ships like a team. Try it with Sonnet 4.5!

🚀 I’m excited to share a big milestone for Emancro! We’ve successfully piloted our AI-powered robot at one of the leading US hospitals taking on one of the most critical and error-prone hospital logistics tasks: medication cabinet restocking. At the core is GEDIA — our proprietary Generalizable Dexterous Intelligent Agent that gives our robots the ability to adapt and perform complex tasks at scale. 👉 Watch the robot in action: (youtube.com/watch?v=QZbx89…) 👉 Learn more about Emancro: (emancro.ai) And this is only the beginning 🤖. We’re already developing our next-gen robot to expand into medical supply distribution, lab sample logistics, food, and linen services — on track to automate the majority of logistics tasks in hospitals and beyond.

One of Outset's earliest bets is launching today! Congratulations @medra_ai on the launch. Bringing AI into the lab is a bold step forward for biotech, and it’s exciting to see this vision come to life.

Head of Engineering at Cursor, Founding Team at Cognition, Research at OpenAI, Founder of Paradigm and DESIGN AT BROWSERBASE!!! @liammatteson crushing it as usual.

At @browserbase, we believe in making the internet more accessible for agents. That's why we're excited to partner with @Cloudflare to support the adoption of Web Bot Auth, a critical layer of identity for agents.

Teamwork makes the dream work (@ttobbaybbob). @outsetcap career fair edition (📸 @RohdeAli @kanjun). Join us @TakoViz!

Your content creation flow just got faster. Veo3 Fast is now live in Hedra! Generate high-motion video fast for less credits than standard Veo3. See the speed for yourself in Hedra Studio.

Reflex just crossed 25k Stars in Github, and is the has been a top trending repository for the past few days!

This is a major role with massive scope and impact. Help us build a science of post-training data curation.

Interesting app someone built with @getreflex and @openrouter - Has built in Auth, Search and Deepthinking built in - Chat with hosted models on openrouter (gemini for general chat, perplexity for web search & cerebras(qwen) for fast response) - Optionally use local models from Ollama and LMStudio when run locally Link + Github below

wtf is MCP? Paul Klein IV, CEO of @browserbase explains "Model Context Protocol" (MCP) in plain terms: "There's this new way that people are exposing tools to AI & the 'Model Context Protocol' is one of those ways that you can standardize & give your AI a set of tools to call. BrowserBase has a way to expose the browser to your agent via MCP or MCP server. More & more developers are trying to find ways to integrate more functionalities to their AI agents & BrowserBase's browsers are one of those primitive functionalities, & the MCP is just one way to integrate it into your software." @pk_iv From 🅱️'s GitHub: Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you’re building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need. This server provides cloud browser automation capabilities using Browserbase and Stagehand. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a cloud browser environment.