正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI... for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.show more

Rohan Paul

151,318 subscribers

33,431 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Claude Code on desktop now has an in-app browser. Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers. It's sandboxed and configurable: you choose whether sessions persist.

Claude Code on desktop now has an in-app browser. Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers. It's sandboxed and configurable: you choose whether sessions persist.

ClaudeDevs

3,370,372 次观看 • 11 天前

Claude Code Desktop can now run your app, catch errors, review code, and merge PRs automatically 🤯 This update closes the entire development loop — from writing to previewing to reviewing to fixing to merging — without you lifting a finger. Want the full guide? DM me.

Claude Code Desktop can now run your app, catch errors, review code, and merge PRs automatically 🤯 This update closes the entire development loop — from writing to previewing to reviewing to fixing to merging — without you lifting a finger. Want the full guide? DM me.

Julian Goldie SEO

12,984 次观看 • 4 个月前

Cursor now has a built-in web browser. You can say "start my app" and it will run the dev server in a terminal and then navigate the browser to localhost:3000. It can take screenshots of the page for iterating on design, and you can send DOM elements to the agent with prompts!

Cursor now has a built-in web browser. You can say "start my app" and it will run the dev server in a terminal and then navigate the browser to localhost:3000. It can take screenshots of the page for iterating on design, and you can send DOM elements to the agent with prompts!

Lee Robinson

216,167 次观看 • 8 个月前

You can now use Claude Code and GitHub CLI directly inside Perplexity Computer. We gave it an open issue on Openclaw. Computer: → Forked the repo → Wrote a plan to fix the bug → Opened Claude Code and implemented it → Submitted a PR via GitHub CLI

You can now use Claude Code and GitHub CLI directly inside Perplexity Computer. We gave it an open issue on Openclaw. Computer: → Forked the repo → Wrote a plan to fix the bug → Opened Claude Code and implemented it → Submitted a PR via GitHub CLI

Computer

416,607 次观看 • 4 个月前

Big drop today with 5.6, ChatGPT work, brand new desktop app, and more! The browser team's been working hard on 3 big updates for today: 1) A more fully functional in-app browser inside the new Desktop App 2) A cloud browser that the agent can use on the go inside the new work mode on & app 3) Side chat that brings the full power of ChatGPT & Codex to your browser

James Sun

24,417 次观看 • 12 天前

Did you know that Visual Studio Code has HAD a built-in browser! Say "start my app in simple browser" and it will run the dev server and open simple browser to localhost. It can take screenshots of the page or element and send DOM elements to the agent chat!

Did you know that Visual Studio Code has HAD a built-in browser! Say "start my app in simple browser" and it will run the dev server and open simple browser to localhost. It can take screenshots of the page or element and send DOM elements to the agent chat!

James Montemagno

47,489 次观看 • 8 个月前

Introducing Conductor code review! You can now comment on diffs and send it straight back to Claude without leaving the app. Like a PR review, but for the AI:

Introducing Conductor code review! You can now comment on diffs and send it straight back to Claude without leaving the app. Like a PR review, but for the AI:

Charlie Holtz

72,969 次观看 • 9 个月前

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.

James Sun

226,445 次观看 • 2 个月前

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

61,757 次观看 • 1 年前

🚀New workflow for creating desktop apps you can run in windows and mac 1⃣ create app in bolt.new 2⃣ download the code from bolt 3⃣ open project in @windsurf 4⃣ ask windsurf to convert it into an electron app 5⃣ run it as a desktop app awesome 🔥🔥🔥 here's how it works 👇

🚀New workflow for creating desktop apps you can run in windows and mac 1⃣ create app in bolt.new 2⃣ download the code from bolt 3⃣ open project in @windsurf 4⃣ ask windsurf to convert it into an electron app 5⃣ run it as a desktop app awesome 🔥🔥🔥 here's how it works 👇

Melvin Vivas

22,743 次观看 • 1 年前

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

Steve (Builder.io)

25,187 次观看 • 22 天前

ANTHROPIC 🔥: Early look at Claude Science, a new app designed for scientific research. > "Artifacts traced to their code, environments managed on demand, and 60+ optional scientific databases that you can connect." Claude Science was named "Operon" during development and is now being distributed as a desktop app. Interestingly, the app acts as a local web server, and its UI runs in your browser. Some unique features include the ability to create dedicated "Categories" in Memory and custom agents called "Specialists". We need this on consumer version too 👀

ANTHROPIC 🔥: Early look at Claude Science, a new app designed for scientific research. > "Artifacts traced to their code, environments managed on demand, and 60+ optional scientific databases that you can connect." Claude Science was named "Operon" during development and is now being distributed as a desktop app. Interestingly, the app acts as a local web server, and its UI runs in your browser. Some unique features include the ability to create dedicated "Categories" in Memory and custom agents called "Specialists". We need this on consumer version too 👀

🚨 AI News | TestingCatalog

47,880 次观看 • 21 天前

Update: You can now modify your created apps easily. Once you create an app, you'll see a popup in the bottom right corner. Simply tell the AI about your requested changes and it whip together the code additions Watch how I add a timer and gamification for each task to a basic todo app 👇 The possibilities are now truly limitless - instead of just making the app and getting it right once, you can now keep iterating until you get what you want. One step closer to the vision of turning 2077 into the most powerful - and fun - coding engine in crypto!

Update: You can now modify your created apps easily. Once you create an app, you'll see a popup in the bottom right corner. Simply tell the AI about your requested changes and it whip together the code additions Watch how I add a timer and gamification for each task to a basic todo app 👇 The possibilities are now truly limitless - instead of just making the app and getting it right once, you can now keep iterating until you get what you want. One step closer to the vision of turning 2077 into the most powerful - and fun - coding engine in crypto!

2077: A Code Quest

20,810 次观看 • 1 年前

How to convert ANY web app into a Mobile App... That can be shipped to the App Store from your phone. (Zero Coding Required) This works with web apps made on Replit, Bolt, v0, Replit or Cursor. Tech Stack: 1. Claude Desktop (works with ChatGPT) 2. - Builds the Mobile app, Ships to App Store directly from the phone (Uses Claude Code) (Prompt for conversion below) TIMESTAMPS Intro The Web App We Will Convert The Mobile App that Builds Mobile Apps Mobile App Version 1 You can Publish this to the App Store Adding Additional Features (AI APIs) to your app Editing the Mobile App with the Select Feature

How to convert ANY web app into a Mobile App... That can be shipped to the App Store from your phone. (Zero Coding Required) This works with web apps made on Replit, Bolt, v0, Replit or Cursor. Tech Stack: 1. Claude Desktop (works with ChatGPT) 2. - Builds the Mobile app, Ships to App Store directly from the phone (Uses Claude Code) (Prompt for conversion below) TIMESTAMPS Intro The Web App We Will Convert The Mobile App that Builds Mobile Apps Mobile App Version 1 You can Publish this to the App Store Adding Additional Features (AI APIs) to your app Editing the Mobile App with the Select Feature

Riley Brown

59,326 次观看 • 8 个月前

CLAUDE CODE JUST GOT EYES Claude Code on desktop can now open and use a real browser, right inside the app. No screenshots, no copy pasting, no separate tools. - It opens docs, designs, or any site next to your code - It clicks, types, and fills forms exactly like a human would - It takes its own screenshots to check if the code actually works - It runs in a clean separate profile, none of your logins touched Your AI coding assistant just stopped being blind.

BuBBliK

49,154 次观看 • 11 天前

I tested Genspark new AI Developer: an L4 agent that builds a working app from an idea. You can choose any model (including Claude), and it runs in your browser and in the app—including planning, code, testing, and fixes. The output looks like it was done by a senior developer. I used Prompt to build a functional newsflash page that creates and curates a newsletter for me by adding a few links! It's revolutionary. Prompt in the comments. Genspark

I tested Genspark new AI Developer: an L4 agent that builds a working app from an idea. You can choose any model (including Claude), and it runs in your browser and in the app—including planning, code, testing, and fixes. The output looks like it was done by a senior developer. I used Prompt to build a functional newsflash page that creates and curates a newsletter for me by adding a few links! It's revolutionary. Prompt in the comments. Genspark

Chubby♨️

235,727 次观看 • 11 个月前

WebMCP is the future of the web. Agents can now interact with any website without ever seeing the UI. I built a starter template to show how: A DoorDash like app where the agent adds items to cart and checks out with the right address + promo code. The browser is now the API.

WebMCP is the future of the web. Agents can now interact with any website without ever seeing the UI. I built a starter template to show how: A DoorDash like app where the agent adds items to cart and checks out with the right address + promo code. The browser is now the API.

Pietro Schirano

168,291 次观看 • 5 个月前

This is a very nice description of the problem. I think the first part of the solution is to not give into the hyper productivity hype: running a gazillion things in parallel. There's likely only a handful of humans that have the mental make-up to survive the permanent context switches. You can train your brain to become better at it, but there's a limit to that, and I found that it will lead to much worse outcomes in terms of output quality of both you and your clanker. I'm no neuroscientist, but I would assume there's a hard limit on how many things your brain can juggle at a time, probably made worse by the complexity that is code. I generally don't do more than 2-3 things in parallel. I use virtual desktops as "bundle of things that belong to a task", so terminals + editor + browser. Works fine, doesn't need any special OS support, expose on the virtual desktop let's me quickly switch to the task specific app I need. I also have a little pi extension that shows me what GH issue/PR the clanker session is about, with a link I can click to open the issue/PR in the browser. Plus 1 virtual desktop for entertainment, so the brain can get some rest. (better alternative: get up and walk a bit every 45 minutes) Video: - First desktop: pi session for a PR, extension shows me what PR I work on, can click to open in browser, aux terminal for random BS, editor, browser. Yes, I could split instead of having two terminal windows. I'm old. - Second desktop: clawdbot pi session, aux terminal for testing, editor, browser - Third desktop: entertainment booth

This is a very nice description of the problem. I think the first part of the solution is to not give into the hyper productivity hype: running a gazillion things in parallel. There's likely only a handful of humans that have the mental make-up to survive the permanent context switches. You can train your brain to become better at it, but there's a limit to that, and I found that it will lead to much worse outcomes in terms of output quality of both you and your clanker. I'm no neuroscientist, but I would assume there's a hard limit on how many things your brain can juggle at a time, probably made worse by the complexity that is code. I generally don't do more than 2-3 things in parallel. I use virtual desktops as "bundle of things that belong to a task", so terminals + editor + browser. Works fine, doesn't need any special OS support, expose on the virtual desktop let's me quickly switch to the task specific app I need. I also have a little pi extension that shows me what GH issue/PR the clanker session is about, with a link I can click to open the issue/PR in the browser. Plus 1 virtual desktop for entertainment, so the brain can get some rest. (better alternative: get up and walk a bit every 45 minutes) Video: - First desktop: pi session for a PR, extension shows me what PR I work on, can click to open in browser, aux terminal for random BS, editor, browser. Yes, I could split instead of having two terminal windows. I'm old. - Second desktop: clawdbot pi session, aux terminal for testing, editor, browser - Third desktop: entertainment booth

Mario Zechner

40,284 次观看 • 5 个月前

Do you want to review a 1-million-line PR? Jarred Sumner did not make it easy for either you or GitHub. Well, Atlas did! You can check how the agent went on to write the code on the left, and understand the line-block changes on the right. Comments in a separate tab.

Do you want to review a 1-million-line PR? Jarred Sumner did not make it easy for either you or GitHub. Well, Atlas did! You can check how the agent went on to write the code on the left, and understand the line-block changes on the right. Comments in a separate tab.

Aravind Putrevu

13,047 次观看 • 2 个月前