Загрузка видео...

Не удалось загрузить видео

На главную

Announcing Chrome DevTools MCP! 🚀 Connect your AI coding agent to Chrome's powerful automation & debugging capabilities with ease. Key features: ✅ Reliable automation: It can programmatically handle clicks, form fills, dialogs, and page navigation with ease. ✅ Performance insights: Go beyond simple audits. Instruct your agent to record...

269,939 просмотров • 1 год назад •via X (Twitter)

Комментарии: 53

Фото профиля Addy Osmani
Addy Osmani1 год назад

Learn more about @ChromeDevTools MCP or checkout our GitHub repo:

Фото профиля Burke Holland
Burke Holland1 год назад

@ChromeDevTools Add it to the MCP Registry! Can't wait to try it out.

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Thanks Burke! We will!

Фото профиля Burke Holland
Burke Holland1 год назад

@ChromeDevTools LOVE the work. Thank you so much!

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools And we love yours!

Фото профиля Hitarth Sharma
Hitarth Sharma1 год назад

@ChromeDevTools @grok how does this compare to the Playwright MCP

Фото профиля Harald Kirschner
Harald Kirschner1 год назад

@ChromeDevTools With all those traces and network data, MCP resources would be a good way to attach to the tool responses so the model can follow up without extra tool calls. But the P0 must be adding MCP prompts for all web performance workflows: /paul, /addy … 🚀

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Super relevant to us! cc @MHablich @mathias

Фото профиля Ahmad Awais
Ahmad Awais1 год назад

@ChromeDevTools This is super helpful.

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Great to hear and hope so! 🙏

Фото профиля Angie Jones
Angie Jones1 год назад

@ChromeDevTools 🔥

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools 🙏

Фото профиля Philipp Schmid
Philipp Schmid1 год назад

@ChromeDevTools Great work! This looks awesome!

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Thanks so much, Philipp!

Фото профиля PAVEL SUKHACHEV
PAVEL SUKHACHEV1 год назад

That's a cool announcement! For folks interested in alternatives: Playwright MCP offers equivalent capabilities like reliable automation (clicks, forms, navigation) Performance tracing for optimizations, advanced debugging (network requests, console logs, screenshots, script eval) And browser emulation (CPU/network throttling, screen sizes)—plus cross-browser support beyond just Chrome. Worth checking out for AI agent workflows.

Фото профиля Eric Clemmons 🍊☁️
Eric Clemmons 🍊☁️1 год назад

@ChromeDevTools Wow, that’s a great demo! Congrats on the launch!

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Thanks so much, Eric!

Фото профиля Han Cheng e/acc
Han Cheng e/acc1 год назад

@ChromeDevTools Nice one

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Thanks!

Фото профиля Balázs Némethi
Balázs Némethi1 год назад

@ChromeDevTools finally!

Фото профиля Brandon Charleson
Brandon Charleson1 год назад

@ChromeDevTools love it!! nice work!

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools 🙏🙏

Фото профиля anotheryou
anotheryou1 год назад

@ChromeDevTools Can it traverse the dom tree without reading it all?

Фото профиля Gavin C.
Gavin C.1 год назад

@ChromeDevTools Can I add it into our Agent?

Фото профиля Atul Jha
Atul Jha1 год назад

@ChromeDevTools NVIDIA is what GCP/AWS/AZURE many years back. They too were investing in late stage startups offering them discounted cloud instances.

Фото профиля Mick.net - Maker: Document.Bot 🤖 BestTime.app 🎉
Mick.net - Maker: Document.Bot 🤖 BestTime.app 🎉1 год назад

@ChromeDevTools Sounds like Playwright mcp, but maybe with more features? Performance insights, evaluate scripts in the browser and more i guess?

Фото профиля Agam Chaudhary
Agam Chaudhary1 год назад

@ChromeDevTools Giving coding agents direct access to Chrome DevTools feels like a shift toward true end to end web development support. From debugging to performance insights this could redefine how devs and agents collaborate. What new use cases do you see emerging first

Фото профиля 🇺🇦 Maks Surguy
🇺🇦 Maks Surguy1 год назад

@ChromeDevTools This is really exciting! Thank you and team!

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Our pleasure! We hope its helpful :)

Фото профиля @andresio
@andresio1 год назад

@ChromeDevTools Can I use this for QA work in chrome extension? :O

Фото профиля Matija Grcic
Matija Grcic1 год назад

@ChromeDevTools The missing piece.

Фото профиля D@RWIN
D@RWIN1 год назад

@ChromeDevTools Addy, this is amazing. Thanks for sharing and big congrats to you and team who worked on this!

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Thanks for the kind words! We're really looking forward to folks kicking tires on it 😀

Фото профиля D@RWIN
D@RWIN1 год назад

@ChromeDevTools I'm relieved I don't have to code this anymore!!

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools Yes! Someone was just asking me how well you can use natural language => DOM. We support this in both our MCP and the AI Assistant in @ChromeDevTools

Фото профиля Prafull
Prafull1 год назад

@ChromeDevTools Could it also help, alongside the "routes" context from the react code, to automate creation of the test suite for end-to-end user journeys?

Фото профиля Engracious
Engracious1 год назад

@ChromeDevTools 🙌🏼🙌🏼🙌🏼

Фото профиля Modern Learner
Modern Learner1 год назад

@ChromeDevTools Very very cool

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools 🙏

Фото профиля Arif
Arif1 год назад

@ChromeDevTools Time to replace Playwright 🙌🏼

Фото профиля Michael Bushe 💙🧘‍♂️🌎⚾
Michael Bushe 💙🧘‍♂️🌎⚾1 год назад

@ChromeDevTools 👏🏻👏🏻👏🏻👏🏻👏🏻👏🏻👏🏻

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools 🙏🙏🙏

Фото профиля Michael Bushe 💙🧘‍♂️🌎⚾
Michael Bushe 💙🧘‍♂️🌎⚾1 год назад

@ChromeDevTools Thank you for all you do!

Фото профиля Ξma Lorenzo
Ξma Lorenzo1 год назад

@ChromeDevTools after adding it shows disabled and 0 tools available, what's the steps or requirements for this to work? things to look to fix? can add it to Cursor and Gemini CLI in the same project?

Фото профиля AIGoldenfinger
AIGoldenfinger1 год назад

@ChromeDevTools Can you help me understand: to use ChromeDevTools I need to have an Anthropic API key to install Claude desckop... or simplified to use google's tool I need to have Claude app installed? Am I missing something or google is skipping something again ?

Фото профиля Sprog
Sprog1 год назад

@techgirl1908 @ChromeDevTools Can it help find memory leaks?

Фото профиля ZX🇨🇦
ZX🇨🇦1 год назад

@ChromeDevTools @grok how does this compare to the @browser_use ?

Фото профиля Alex Martossy
Alex Martossy1 год назад

@ChromeDevTools Cool. I don't see any tool for actually reading the page. That kinda defeats the purpose, no?

Фото профиля Addy Osmani
Addy Osmani1 год назад

@ChromeDevTools We do indeed have tools for this including take_snapshot

Фото профиля Alex Martossy
Alex Martossy1 год назад

@ChromeDevTools Nice

Фото профиля 南北西东
南北西东1 год назад

@ChromeDevTools The amount of time I've wasted guessing at performance issues from the outside... Giving agents direct debugger and profiler access is the superpower we've been waiting for.

Фото профиля Min Chon Chi
Min Chon Chi1 год назад

@ChromeDevTools Seamless Chrome integration is a big plus for developers. Looking forward to seeing how this improves AI agent workflows.

Фото профиля Tikonu
Tikonu1 год назад

@ChromeDevTools oooooooo gonna have fun with this

Похожие видео

🚨 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 просмотров • 1 месяц назад

OpenApp Staking & App Listing Pi Network OpenApp Nicolas Kokkalis Chengdiao Fan Pi Network is home to millions of engaged Pioneers actively exploring apps, services, and digital opportunities within the ecosystem. For developers, creators, and businesses, one of the biggest challenges is visibility—how can great apps reach the right users? OpenApp Staking & App Listing was created to solve that challenge. OpenApp provides a decentralized discovery platform where developers can list their Pi-powered applications and use staking to increase their visibility within the OpenApp directory. By staking, apps gain greater exposure to the community, helping attract more users, engagement, and growth opportunities. This creates a self-service ecosystem where builders can leverage Pi to promote their projects while allowing Pioneers to discover innovative applications more easily. As technology and AI continue to make app development faster and more accessible, the real challenge becomes user acquisition and discovery. OpenApp bridges that gap by providing: ✅ App Listing & Discovery ✅ Directory Staking for Increased Visibility ✅ Featured App Promotions ✅ Category-Based Rankings ✅ Pioneer-Friendly App Exploration ✅ Support for Mainnet, Testnet, and Beta Apps Whether you're launching a new project or growing an existing one, OpenApp helps connect your application with the Pi community and gives users a simple way to discover the best apps in the ecosystem. 🚀 List Your App: 📚 Learn More: OpenApp — Discover. Publish. Grow.

Mrwain Organization

13,901 просмотров • 4 месяцев назад

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,256 просмотров • 1 год назад

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 просмотров • 1 год назад