Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a... show more

Paul Klein IV

20,649 subscribers

1,732,241 views • 7 months ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

70 Comments

greg7 months ago

I have no idea what an API is and at this point it doesn’t seem like I need to know

Paul Klein IV7 months ago

let your agent figure it out!

Ramp7 months ago

We <3 Browserbase We <3 agents We <3 Browserbase agents It's simple

Paul Klein IV7 months ago

It's simple Ramp + Browserbase = <3

Guillermo Rauch7 months ago

Epic work, congrats. I legit hear from so. many. happy @vercel + @browserbase customers every single week… 👏🅱️🌑

Paul Klein IV7 months ago

@vercel @browserbase Thanks G! Appreciate your continued support.

Paul Klein IV7 months ago

Read more on our brand new website and blog:

Tiffany Fong7 months ago

i’m never gonna do online chores ever again 🙏

Paul Klein IV7 months ago

agents will do everything that we don't want to

mads campbell7 months ago

my search history today is just “does (insert website here) have an api key”

Paul Klein IV7 months ago

got an API key for you right here 🤝

Alex Volkov7 months ago

Congrats! Repping from London! Thanks for the Shwag!

Paul Klein IV7 months ago

spread the word worldwide

Stagehand7 months ago

build the best browser agents with stagehand (now in green)

Paul Klein IV7 months ago

brat summer is coming

Erika⚡️⚡️7 months ago

“My agent gets stuck on Craigslist. My agent sucks at booking my flights. Why can’t my open claw buy my groceries” Because you need a browser that works. Use ours, now with fetch / search / runtime / +++ We’re just getting started. Woof 🤠🤠

Paul Klein IV7 months ago

We're out here on riding the wild web 🤠

flora ٩(ˊᗜˋ)و*7 months ago

new brand new brand new brand

Paul Klein IV7 months ago

brand new brand new brand new

flora ٩(ˊᗜˋ)و*7 months ago

brand new brand

Jonathan Taylor7 months ago

@browserbase - The one API for Agents to rule whole Middle Internet

Paul Klein IV7 months ago

@browserbase "Even the smallest API Key can change the course of the future" - Gandalf

christina cook7 months ago

we're just getting started wrangling the web. 🤠 so proud of the team!!

Paul Klein IV7 months ago

yeeehaw!

Nick Khami7 months ago

new logo is looking great 💅

Paul Klein IV7 months ago

thanks nick!

Hannah Swann7 months ago

Heck yes!! Looks so good! 🔥 Was great to collab on all the brand stuff.

Paul Klein IV7 months ago

loveee this graphic!

Hannah Swann7 months ago

🔥woo! thanks! I think @liammatteson already copped a version of it :)

Ziray Hao7 months ago

we'll automate all the 3 letter acronyms, API, MCP, USA

Paul Klein IV7 months ago

CLI

Nikhil Kulkarni7 months ago

@shreypandya is gonna have to click so much holy shit Congrats y'all :)

Paul Klein IV7 months ago

@shreypandya we're hiring more engineers too help

Liam7 months ago

it’s time to bring agents online!! 🌐⛰️

Paul Klein IV7 months ago

loading new agents..... 💾

joshpuckett7 months ago

I am so excited I can finally make my Pro Cycling Situation Monitor instead of waiting for the UCI to release an API in 2045 🙌

Paul Klein IV7 months ago

we need to plug this into @Polymarket

joshpuckett7 months ago

@Polymarket

sarah richard7 months ago

Finally!!! So excited we can finally share that Browserbase is now the one stop shop to make the web reliable for your agents

Paul Klein IV7 months ago

So glad we get to build this together!

Historic Vids7 months ago

This is interesting, I would never have thought of this

Paul Klein IV7 months ago

imagine what you could do if AI could do everything you could

Aaron Francis7 months ago

oh hey new branding!

Paul Klein IV7 months ago

🅱️

Aaron Francis7 months ago

nit: needs more orange

harsehaj ⋆˙⟡7 months ago

no more keyblocking the agents !!!!

Kyle Jeong7 months ago

brb building agents to do my job on my behalf

Paul Klein IV7 months ago

brb building agents that capture attention

Peyton Casper7 months ago

browserbase is growing up 🥹

Michael7 months ago

I didn't know you shipped half this stuff! Looks like I have some homework to read through

Charly Poly7 months ago

Web >>> APIs

Paul Klein IV7 months ago

web >>>>>>>>>>>> APIs

Shubhankar7 months ago

The best agents browse on Browserbase!

Paul Klein IV7 months ago

they’re already out there!

❄️7 months ago

How do we get to 0 api keys

Paul Klein IV7 months ago

just one more api key bro please

Mark Vassilevskiy7 months ago

Let's gooo!

nico7 months ago

browserbase stays winning

Paul Klein IV7 months ago

miss you man!

nico7 months ago

same same 🫶

jihad7 months ago

"give your agent the whole web" whoever came up with that tagline cooked

Paul Klein IV7 months ago

amazing work from @whereischarly

samyok7 months ago

epic launch

Paul Klein IV7 months ago

thank you thank you

Utpal Nadiger7 months ago

damn the new branding slaps! congrats on the launch :)

Paul Klein IV7 months ago

here's how we made it!

alana goyal7 months ago

!!!!!!!!!!!

Paul Klein IV7 months ago

👀 swag box waiting in your office

Sarah Chieng7 months ago

Absolutely incredible, Paul and team.

Paul Klein IV7 months ago

thank you for always supporting us sarah!!!

Related Videos

Agents need their own identity to do real work on the web. We partnered with Ramp to automate our event logistics workflow. Our agent logs into sites with a Browserbase Context, downloads receipts, and submits them via the Ramp CLI.

Agents need their own identity to do real work on the web. We partnered with Ramp to automate our event logistics workflow. Our agent logs into sites with a Browserbase Context, downloads receipts, and submits them via the Ramp CLI.

Browserbase

23,753 views • 2 months ago

Build agents with LangChain + Browserbase. Give your Deep Agents search, fetch, and browser subagents to access the full web. All with full observability with the Browserbase dashboard.

Build agents with LangChain + Browserbase. Give your Deep Agents search, fetch, and browser subagents to access the full web. All with full observability with the Browserbase dashboard.

LangChain

48,004 views • 6 months ago

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Firecrawl

123,983 views • 6 months ago

Somebody just created an API to instagram with 1 single prompt to this agent. With this agents can finally interact with anything reliable on the web.

Somebody just created an API to instagram with 1 single prompt to this agent. With this agents can finally interact with anything reliable on the web.

Magnus Müller

29,339 views • 11 months ago

/web Creates a web. md file for any website. Every page, action, flow, and interactive element your coding agent needs to navigate it. AI agents fail on websites because they don't know the structure. Web. md gives them the map before they start ↓

/web Creates a web. md file for any website. Every page, action, flow, and interactive element your coding agent needs to navigate it. AI agents fail on websites because they don't know the structure. Web. md gives them the map before they start ↓

Hyperbrowser

71,707 views • 5 months ago

Your agents can now browse and take actions on the web, just like you can. This lets agents work with sites that don’t have APIs and still complete tasks end to end. Plus, each interaction is streamed live to Studio.

Your agents can now browse and take actions on the web, just like you can. This lets agents work with sites that don’t have APIs and still complete tasks end to end. Plus, each interaction is streamed live to Studio.

Mastra

16,848 views • 6 months ago

The web was built for humans. And honestly, that's fine for you guys. But the next trillion internet users are AI agents, robots, and devices who act on your behalf - booking appointments, filling forms, placing orders, and getting things done - using sites that will never, ever have APIs. 95% of the economy falls into this Deep Web of HTML mess designed for humans, not agents. Oh, those generic computer use agents aren't taking you anywhere. They're too slow, too expensive, they hallucinate, and are nondeterministic to rely on. That changes now. This is me, Mino, a web agents API to build on this Deep Web. I take a goal in simple language and execute it on websites that were never meant to be automated. Massive companies like Google, DoorDash, ClassPass are already using me to do their homework. Now it’s your turn. How though? I actually understand what's on the page - parsing structure and identifying elements. I use AI once to understand everything, codify my successes, and get better and faster with every run. You get: → 85-95% success rate on complex workflows → Pennies per job (stop wasting $$ on one job) → Parallel execution across multiple sites → Structured JSON outputs. Every. Single. Time. The web wasn't built for agents. I forced it to work anyway. Go build something real. 50 completed runs on the house:

The web was built for humans. And honestly, that's fine for you guys. But the next trillion internet users are AI agents, robots, and devices who act on your behalf - booking appointments, filling forms, placing orders, and getting things done - using sites that will never, ever have APIs. 95% of the economy falls into this Deep Web of HTML mess designed for humans, not agents. Oh, those generic computer use agents aren't taking you anywhere. They're too slow, too expensive, they hallucinate, and are nondeterministic to rely on. That changes now. This is me, Mino, a web agents API to build on this Deep Web. I take a goal in simple language and execute it on websites that were never meant to be automated. Massive companies like Google, DoorDash, ClassPass are already using me to do their homework. Now it’s your turn. How though? I actually understand what's on the page - parsing structure and identifying elements. I use AI once to understand everything, codify my successes, and get better and faster with every run. You get: → 85-95% success rate on complex workflows → Pennies per job (stop wasting $$ on one job) → Parallel execution across multiple sites → Structured JSON outputs. Every. Single. Time. The web wasn't built for agents. I forced it to work anyway. Go build something real. 50 completed runs on the house:

TinyFish

656,876 views • 10 months ago

defining a new category: phone-use an mcp/api that gives ai agents their own phones cloud phones. real androids. real iphones. tell your agent what to do, and it can operate a phone just like you do. today, ai agents face three fundamental problems and phoneuse solves them 🧵

defining a new category: phone-use an mcp/api that gives ai agents their own phones cloud phones. real androids. real iphones. tell your agent what to do, and it can operate a phone just like you do. today, ai agents face three fundamental problems and phoneuse solves them 🧵

Abdulla Ababakre

2,614,597 views • 16 days ago

Not enough people know about Managed Agents 😀 In a single API call you get the Antigravity harness running in a cloud sandbox where it can write code, search the web, connect to MCP servers etc. Build them into your products or teach an agent to do your repetitive daily tasks.

Not enough people know about Managed Agents 😀 In a single API call you get the Antigravity harness running in a cloud sandbox where it can write code, search the web, connect to MCP servers etc. Build them into your products or teach an agent to do your repetitive daily tasks.

Jack Wotherspoon

10,732 views • 17 days ago

INCREDIBLE!! An MCP server to browse the web like humans! Bright Data MCP server provides 30+ powerful tools that allow AI agents to access, search, crawl, and interact with the web without getting blocked. 100% open-source, works at scale!

INCREDIBLE!! An MCP server to browse the web like humans! Bright Data MCP server provides 30+ powerful tools that allow AI agents to access, search, crawl, and interact with the web without getting blocked. 100% open-source, works at scale!

Akshay 🚀

90,404 views • 1 year ago

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

Andrew Ng

186,182 views • 1 year ago

The real challenge isn’t building agents. It’s discovering them. Trusting them. Coordinating them. Just like the early web had millions of websites, agentic AI will have millions of autonomous agents. Now, agents need infrastructure to find, verify, and work with other agents. Listen to Humayun discuss how to make the process secure, autonomous and scalable.

The real challenge isn’t building agents. It’s discovering them. Trusting them. Coordinating them. Just like the early web had millions of websites, agentic AI will have millions of autonomous agents. Now, agents need infrastructure to find, verify, and work with other agents. Listen to Humayun discuss how to make the process secure, autonomous and scalable.

Fetch.ai

12,072 views • 8 months ago

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

Vikas gupta

20,121 views • 2 months ago

Firecrawl open-sourced "web-agent," a new framework that allows developers to build AI agents capable of autonomously executing "search-scrape-interact" loops on the live web. By running a single command, developers can scaffold a complete project with streaming UI, API, or library templates. The framework uses a "Plan-Act" mechanism and can spin up parallel sub-agents to process multiple websites simultaneously. It is entirely model-agnostic, allowing you to plug in OpenAI, Anthropic (with recent builds defaulting to Claude Opus 4.7), or your own self-hosted models.

Firecrawl open-sourced "web-agent," a new framework that allows developers to build AI agents capable of autonomously executing "search-scrape-interact" loops on the live web. By running a single command, developers can scaffold a complete project with streaming UI, API, or library templates. The framework uses a "Plan-Act" mechanism and can spin up parallel sub-agents to process multiple websites simultaneously. It is entirely model-agnostic, allowing you to plug in OpenAI, Anthropic (with recent builds defaulting to Claude Opus 4.7), or your own self-hosted models.

Wes Roth

53,653 views • 6 months ago

Browser/Computer Automation Jared Friedman AI agents can now browse the web and use desktop applications. It means that every website and every app now effectively has an API, and any workflow that people can do on a computer can be automated.

Browser/Computer Automation Jared Friedman AI agents can now browse the web and use desktop applications. It means that every website and every app now effectively has an API, and any workflow that people can do on a computer can be automated.

Y Combinator

62,191 views • 1 year ago

it seems like agentic commerce is finally solved with stripe link. and we're excited to partner with stripe to enable all agents to transact online. your agent can now natively make payments on the web using link cli + browserbase. one shot prompt:

it seems like agentic commerce is finally solved with stripe link. and we're excited to partner with stripe to enable all agents to transact online. your agent can now natively make payments on the web using link cli + browserbase. one shot prompt:

Paul Klein IV

37,468 views • 1 month ago

🦞Introducing BaseClaw Built on Base App as a miniapp where you can 1 click launch your own agent with your API key - For now it's all free with your API key (including web search) but hybrid model will coming soon, where you won't even need a key. - Save your agents and chats, came back to them later. - 12+ model support (openrouter included) - Everything onchain, on BaseApp - All built with OpenClaw🦞 Wallet and payment integrations (x402) and agent token launch features coming sooner than you think. Launch will be on Virtuals Protocol

🦞Introducing BaseClaw Built on Base App as a miniapp where you can 1 click launch your own agent with your API key - For now it's all free with your API key (including web search) but hybrid model will coming soon, where you won't even need a key. - Save your agents and chats, came back to them later. - 12+ model support (openrouter included) - Everything onchain, on BaseApp - All built with OpenClaw🦞 Wallet and payment integrations (x402) and agent token launch features coming sooner than you think. Launch will be on Virtuals Protocol

wi/tch

20,360 views • 8 months ago

NOW you can BUILD REAL Multi-Modal Agents with our API! 🚀 Excited to announce our API is now publicly available Memories.ai 😃 Memories.ai is building the visual memory layer for AI, it enables AI to see and remember like humans do. 2025 is the year of agents, 2026 is the year of multi-modal agents! 🌟

NOW you can BUILD REAL Multi-Modal Agents with our API! 🚀 Excited to announce our API is now publicly available Memories.ai 😃 Memories.ai is building the visual memory layer for AI, it enables AI to see and remember like humans do. 2025 is the year of agents, 2026 is the year of multi-modal agents! 🌟

Shawn Shen

530,739 views • 1 year ago

If your agents are just personal helpers, you are still the bottleneck. We just introduced Workspaces: a new way for agents and humans to work together with shared skills and memories. Agents need the freedom to operate like real members of your team, invoking other agents and humans to get work done. Many agents + many humans in one shared workspace.

If your agents are just personal helpers, you are still the bottleneck. We just introduced Workspaces: a new way for agents and humans to work together with shared skills and memories. Agents need the freedom to operate like real members of your team, invoking other agents and humans to get work done. Many agents + many humans in one shared workspace.

Hyperagent

33,070 views • 1 month ago

Agents shouldn't see your secrets. Today, most deployments hand the agent a real API key and hope for the best. That's why we're launching Infisical Agent Proxy. You give an agent a fake API key. The agent uses that key and the proxy swaps it for the real one at the network boundary before forwarding it outbound to its destination. An agent can't leak a secret it never sees. Build and deploy AI agents securely with Infisical Agent Proxy.

Agents shouldn't see your secrets. Today, most deployments hand the agent a real API key and hope for the best. That's why we're launching Infisical Agent Proxy. You give an agent a fake API key. The agent uses that key and the proxy swaps it for the real one at the network boundary before forwarding it outbound to its destination. An agent can't leak a secret it never sees. Build and deploy AI agents securely with Infisical Agent Proxy.

Infisical

29,214 views • 3 months ago