Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Announcing Chrome DevTools MCP! ๐Ÿš€ Connect your AI coding agent to Chrome's powerful automation & debugging capabilities with ease. Key features: โœ… Reliable automation: It can programmatically handle clicks, form fills, dialogs, and page navigation with ease. โœ… Performance insights: Go beyond simple audits. Instruct your agent to record...

269,939 Aufrufe โ€ข vor 1 Jahr โ€ขvia X (Twitter)

53 Kommentare

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

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

Profilbild von Burke Holland
Burke Hollandvor 1 Jahr

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

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools Thanks Burke! We will!

Profilbild von Burke Holland
Burke Hollandvor 1 Jahr

@ChromeDevTools LOVE the work. Thank you so much!

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools And we love yours!

Profilbild von Hitarth Sharma
Hitarth Sharmavor 1 Jahr

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

Profilbild von Harald Kirschner
Harald Kirschnervor 1 Jahr

@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 โ€ฆ ๐Ÿš€

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

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

Profilbild von Ahmad Awais
Ahmad Awaisvor 1 Jahr

@ChromeDevTools This is super helpful.

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools Great to hear and hope so! ๐Ÿ™

Profilbild von Angie Jones
Angie Jonesvor 1 Jahr

@ChromeDevTools ๐Ÿ”ฅ

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools ๐Ÿ™

Profilbild von Philipp Schmid
Philipp Schmidvor 1 Jahr

@ChromeDevTools Great work! This looks awesome!

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools Thanks so much, Philipp!

Profilbild von PAVEL SUKHACHEV
PAVEL SUKHACHEVvor 1 Jahr

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)โ€”plus cross-browser support beyond just Chrome. Worth checking out for AI agent workflows.

Profilbild von Eric Clemmons ๐ŸŠโ˜๏ธ
Eric Clemmons ๐ŸŠโ˜๏ธvor 1 Jahr

@ChromeDevTools Wow, thatโ€™s a great demo! Congrats on the launch!

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools Thanks so much, Eric!

Profilbild von Han Cheng e/acc
Han Cheng e/accvor 1 Jahr

@ChromeDevTools Nice one

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools Thanks!

Profilbild von Balรกzs Nรฉmethi
Balรกzs Nรฉmethivor 1 Jahr

@ChromeDevTools finally!

Profilbild von Brandon Charleson
Brandon Charlesonvor 1 Jahr

@ChromeDevTools love it!! nice work!

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools ๐Ÿ™๐Ÿ™

Profilbild von anotheryou
anotheryouvor 1 Jahr

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

Profilbild von Gavin C.
Gavin C.vor 1 Jahr

@ChromeDevTools Can I add it into our Agent?

Profilbild von Atul Jha
Atul Jhavor 1 Jahr

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

Profilbild von Mick.net - Maker: Document.Bot ๐Ÿค– BestTime.app ๐ŸŽ‰
Mick.net - Maker: Document.Bot ๐Ÿค– BestTime.app ๐ŸŽ‰vor 1 Jahr

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

Profilbild von Agam Chaudhary
Agam Chaudharyvor 1 Jahr

@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

Profilbild von ๐Ÿ‡บ๐Ÿ‡ฆ Maks Surguy
๐Ÿ‡บ๐Ÿ‡ฆ Maks Surguyvor 1 Jahr

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

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools Our pleasure! We hope its helpful :)

Profilbild von @andresio
@andresiovor 1 Jahr

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

Profilbild von Matija Grcic
Matija Grcicvor 1 Jahr

@ChromeDevTools The missing piece.

Profilbild von D@RWIN
D@RWINvor 1 Jahr

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

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools Thanks for the kind words! We're really looking forward to folks kicking tires on it ๐Ÿ˜€

Profilbild von D@RWIN
D@RWINvor 1 Jahr

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

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@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

Profilbild von Prafull
Prafullvor 1 Jahr

@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?

Profilbild von Engracious
Engraciousvor 1 Jahr

@ChromeDevTools ๐Ÿ™Œ๐Ÿผ๐Ÿ™Œ๐Ÿผ๐Ÿ™Œ๐Ÿผ

Profilbild von Modern Learner
Modern Learnervor 1 Jahr

@ChromeDevTools Very very cool

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools ๐Ÿ™

Profilbild von Arif
Arifvor 1 Jahr

@ChromeDevTools Time to replace Playwright ๐Ÿ™Œ๐Ÿผ

Profilbild von Michael Bushe ๐Ÿ’™๐Ÿง˜โ€โ™‚๏ธ๐ŸŒŽโšพ
Michael Bushe ๐Ÿ’™๐Ÿง˜โ€โ™‚๏ธ๐ŸŒŽโšพvor 1 Jahr

@ChromeDevTools ๐Ÿ‘๐Ÿป๐Ÿ‘๐Ÿป๐Ÿ‘๐Ÿป๐Ÿ‘๐Ÿป๐Ÿ‘๐Ÿป๐Ÿ‘๐Ÿป๐Ÿ‘๐Ÿป

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools ๐Ÿ™๐Ÿ™๐Ÿ™

Profilbild von Michael Bushe ๐Ÿ’™๐Ÿง˜โ€โ™‚๏ธ๐ŸŒŽโšพ
Michael Bushe ๐Ÿ’™๐Ÿง˜โ€โ™‚๏ธ๐ŸŒŽโšพvor 1 Jahr

@ChromeDevTools Thank you for all you do!

Profilbild von ฮžma Lorenzo
ฮžma Lorenzovor 1 Jahr

@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?

Profilbild von AIGoldenfinger
AIGoldenfingervor 1 Jahr

@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 ?

Profilbild von Sprog
Sprogvor 1 Jahr

@techgirl1908 @ChromeDevTools Can it help find memory leaks?

Profilbild von ZX๐Ÿ‡จ๐Ÿ‡ฆ
ZX๐Ÿ‡จ๐Ÿ‡ฆvor 1 Jahr

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

Profilbild von Alex Martossy
Alex Martossyvor 1 Jahr

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

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

@ChromeDevTools We do indeed have tools for this including take_snapshot

Profilbild von Alex Martossy
Alex Martossyvor 1 Jahr

@ChromeDevTools Nice

Profilbild von ๅ—ๅŒ—่ฅฟไธœ
ๅ—ๅŒ—่ฅฟไธœvor 1 Jahr

@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.

Profilbild von Min Chon Chi
Min Chon Chivor 1 Jahr

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

Profilbild von Tikonu
Tikonuvor 1 Jahr

@ChromeDevTools oooooooo gonna have fun with this

ร„hnliche Videos

๐Ÿšจ THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read whatโ€™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 โ€” crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: โ†’ 173,000+ GitHub stars โ†’ Search, scrape and interact with the web at scale โ†’ Supports web pages, PDFs, DOCX and other content โ†’ Structured data extraction for AI workflows โ†’ MCP support for connecting it directly to AI agents The workflow looks like this: Search โ†’ Scrape โ†’ Crawl โ†’ Extract โ†’ 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 Aufrufe โ€ข vor 1 Monat

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 visibilityโ€”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: โœ… App Listing & Discovery โœ… Directory Staking for Increased Visibility โœ… Featured App Promotions โœ… Category-Based Rankings โœ… Pioneer-Friendly App Exploration โœ… 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. ๐Ÿš€ List Your App: ๐Ÿ“š Learn More: OpenApp โ€” Discover. Publish. Grow.

Mrwain Organization

13,901 Aufrufe โ€ข vor 4 Monaten

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. Youโ€™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. Hereโ€™s what youโ€™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 Anthropicโ€™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 Aufrufe โ€ข vor 1 Jahr

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 errorโ€”like clicking the wrong button or misreading a fieldโ€”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 directionsโ€”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 Aufrufe โ€ข vor 1 Jahr