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。

Introducing Tapkit Tapkit is a Mac app that lets your agents use your iPhone. Tell it to do anything and it can use your phone to do it. We've been iterating on Tapkit over the last few months with our earliest users and finally feel like it's ready for... show more

teej

9,337 subscribers

489,851 次观看 • 1 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

74 条评论

rinko 的头像

rinko1 天前

look at that subtle brick wall. the tasteful ruggedness of it. oh my god. there's even a plant

teej 的头像

teej1 天前

"the ink, is that B2 Bomber Black?"

Buyside Guy 的头像

Buyside Guy1 天前

Some feedback from my Claude who already drives my iPhone through Appium, for what it’s worth: Honestly, no, not for what you use the phone for today. It does the same job with a nicer setup, and it would cost you something on privacy. What Tapkit is: a Mac app that lets agents tap, swipe and type on a real iPhone, over cable or Wi-Fi. Agents drive it through an MCP server or a REST API. $49 a month per phone. What we already have: the agent iPhone does all of that through Appium. It reads the screen as text, taps by label, installs apps, signs in with saved passwords and reads 2FA codes from banners. It also queues agents so two don't fight over the phone. Its signing lasts until September 2027 and renews itself. Where it might be better, though I can't confirm any of it: - Stuck prompts: its site says it handles locking, unlocking and 2FA. On Sunday a stuck passcode prompt blocked our phone for hours and needed you there in person. If Tapkit clears those on its own, that's a real gain, but the site doesn't say how. - Reliability: it doesn't depend on Xcode's test tooling, which is what broke on Sunday. - Fewer moving parts: no Xcode, and no helper app to rebuild. Where it's worse: - Privacy: it sends commands through their API, and the site doesn't say whether your screen passes through their servers. That phone shares your Apple ID, so your iMessages land on it. I wouldn't send that screen to a startup that launched today without reading its privacy policy first. - Cost: $49 a month for something that already works. - Unknown: it's brand new, so nobody knows yet how reliable it is. My take: skip it for now. If the phone jams on a stuck prompt again and our fix doesn't hold, that's the moment to trial it on the agent iPhone. Only after the privacy policy confirms your screen stays on the Mac.

teej 的头像

teej1 天前

appreciate the look, this is pretty spot on. my take on the appium stuff is that its literally for testing, automation is an after thought and then agentic use is an after after thought tapkit is a platform that makes your iphones max useful to your agents with minimum setup building something on your own is always an option but not everyone is technical enough to do all of that developer mode on its own is also a massive security risk FWIW and we don't require that

teej 的头像

teej1 天前

trust will for sure be built over time, we wanted it to be easy so we made some product decisions, more ways to use tapkit will be unlocked in the future!

Caelin 的头像

Caelin1 天前

How is this compared to appium or existing open source solutions?

teej 的头像

teej1 天前

we don't require any developer mode or xcode downloads, it's also fully productized so as a user you dont have to do anything or put anything on your phone, just use the app or connect it to your agents

Tom Bielecki 的头像

Tom Bielecki1 天前

@caelin_sutch Huge. Nicely done!

teej 的头像

teej1 天前

@caelin_sutch Thank you Tom!

Griffin McShane 的头像

Griffin McShane1 天前

I was gatekeeping Tapkit for a while now, but feel like its time to give it up...

teej 的头像

teej1 天前

You’ll always be my favorite user

Griffin McShane 的头像

Griffin McShane23 小时前

ily

los (appstar) 的头像

los (appstar)1 天前

huge

teej 的头像

teej1 天前

massive

Denis 的头像

Denis1 天前

@mrinko so i can finally give my eyes a break from staring at screens all day

teej 的头像

teej1 天前

@mrinko Exactly! Only do the things you want

Denis 的头像

Denis1 天前

@mrinko Tweeting?

Noot 的头像

Noot1 天前

banger vid & an insanely useful product almost ready to make a vid using tapkit + an automated conveyor belt setup to scan, sort and list 2000 bulk TCG cards👀 the possibilities are endless

teej 的头像

teej1 天前

we should get it to rip packs

Noot 的头像

Noot1 天前

🤔🤔🤔 you might be onto something here

Treggs 的头像

Treggs1 天前

...and if we don't have an iPhone?

teej 的头像

teej1 天前

then you can buy one and keep it plugged into your mac

Adam | Unruggable 的头像

Adam | Unruggable1 天前

🔥

teej 的头像

teej1 天前

we're so back

Dmytro Virych 的头像

Dmytro Virych1 天前

one Mac driving a whole row of iPhones is a wild demo. running multiple phones at once opens up so much for app testing too

teej 的头像

teej1 天前

many use cases

Connor Grant 的头像

Connor Grant1 天前

Lets gooo, so sick!

teej 的头像

teej1 天前

ty sir!!

sharoz javaid 的头像

sharoz javaid1 天前

is this useful for anything other than marketing on social media

teej 的头像

teej1 天前

it can literally do anything

greg 的头像

greg1 天前

bruh your personal assistant has still been getting blocked on Amazon? mine uses the iOS app…

teej 的头像

teej1 天前

skill issues, just use an iphone

SIP 的头像

SIP1 天前

lezgooooooo

teej 的头像

teej1 天前

We’re in prod!!

Jackson Greathouse Fall 的头像

Jackson Greathouse Fall1 天前

As if TJ’s Hinge game wasn’t already a knockout 10/10, it’s so over for the rest of us Congrats on the launch! This is sick

teej 的头像

teej1 天前

only one thing to do post agi, go on hinge dates

Sadok 的头像

Sadok1 天前

the desk setup is getting out of hand

teej 的头像

teej1 天前

it can do more

1biryazilimci 的头像

1biryazilimci1 天前

what is the difference between using the mac's iphone mirroring app with chatgpt?

teej 的头像

teej1 天前

a few things - the iphone mirror app has limits on what you can do, like payments - the iphone mirror app is limited to the same icloud, so a second phone wouldn't work - the iphone mirror app only does one phone at a time - chatgpt is the best at computer use but you cant like hook it up to muse or grok then

Bobby Thakkar 的头像

Bobby Thakkar1 天前

@edgarpavlovsky Sick

teej 的头像

teej1 天前

@edgarpavlovsky ty king

koreanpeptides 的头像

koreanpeptides1 天前

the launch video is 👏👏👏

teej 的头像

teej1 天前

made with @fal !!!

Will Tholke 的头像

Will Tholke1 天前

Is this open source? Looks cool!

teej 的头像

teej1 天前

Nope! But it’s available to use today!

Will Tholke 的头像

Will Tholke1 天前

What do you think about utilizing it for demo recordings?

Jonathan Amdahl 的头像

Jonathan Amdahl1 天前

Tested this for ~1 month. Helped me clean up my storage, setup up automations, and extract info from my phone to my pc. Huge QOL improvement tbh

teej 的头像

teej1 天前

it's only getting better!

SENTINELITE 的头像

SENTINELITE1 天前

Super awesome product. Excited to dive into it!

teej 的头像

teej1 天前

ty!!

Alton Wells 的头像

Alton Wells1 天前

going to try some experiments with this

teej 的头像

teej1 天前

pls hare the experiments and their results

Rahul Singh Bhadoriya 的头像

Rahul Singh Bhadoriya1 天前

Sexy

teej 的头像

teej1 天前

i know right

Kailash Sarma 的头像

Kailash Sarma1 天前

I’ve been looking for this for ages

teej 的头像

teej1 天前

We built this for you! Dm me anything it doesn’t do and I’ll prioritize it

StruvusMaximus 的头像

StruvusMaximus1 天前

Just use omarchy with screen mirror app

teej 的头像

teej1 天前

Yes! We are macOS only

Cris Lenta 的头像

Cris Lenta1 天前

i so need this holy shit. does it actually work?

teej 的头像

teej1 天前

it works real nice, and if something doesnt work, lmk and i'll fix it

Arihant 的头像

Arihant23 小时前

hell yeah tap tap

ekaksh janweja 的头像

ekaksh janweja1 天前

seems pretty cool!!!

teej 的头像

teej1 天前

ty !!

Burger Bob 🍔 的头像

Burger Bob 🍔1 天前

@edgarpavlovsky Bullish🔥

DinoDeer 的头像

DinoDeer1 天前

That's cool

teej 的头像

teej1 天前

ty

Von.ETH 的头像

Von.ETH1 天前

multiple iphones at once is wild lol

teej 的头像

teej1 天前

up to 7 right now lol

Tovi 的头像

Tovi23 小时前

@FwazSol Lfg tj!

Clive 的头像

Clive1 天前

Good stuff @tj_littlejohn

teej 的头像

teej1 天前

Ty!

Agrim Jain 的头像

Agrim Jain1 天前

This might get viral

teej 的头像

teej1 天前

Ohhhh boy I sure hope so

相关视频

Google offers a AI-powered personal assistant that you can use for free. You can talk to it in real time, share your screen with it, and ask it to help you with any given task (sound on 👇). Surprisingly, not many people are using it. Here's how to use it:

Google offers a AI-powered personal assistant that you can use for free. You can talk to it in real time, share your screen with it, and ask it to help you with any given task (sound on 👇). Surprisingly, not many people are using it. Here's how to use it:

Mushtaq Bilal, PhD

44,549 次观看 • 1 年前

Now you can use your favorite AI agent to control your Coinbase account (or a sub-account), with Coinbase for Agents. Here’s a quick demo on how to set it up and some of the cool things you can get your agent to do.

Now you can use your favorite AI agent to control your Coinbase account (or a sub-account), with Coinbase for Agents. Here’s a quick demo on how to set it up and some of the cool things you can get your agent to do.

Brian Armstrong

213,812 次观看 • 3 个月前

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 次观看 • 7 个月前

"We've move to Resend for so much of our marketing communications. Why? Our AI Agents can talk to it. So easily. And that means we can vibe with it. We can get it to do almost anything we want it to do. That's the new bar today." The latest Agents #002 is out!

"We've move to Resend for so much of our marketing communications. Why? Our AI Agents can talk to it. So easily. And that means we can vibe with it. We can get it to do almost anything we want it to do. That's the new bar today." The latest Agents #002 is out!

Jason ✨👾SaaStr.Ai✨ Lemkin

18,823 次观看 • 5 个月前

Google NotebookLM is absolutely insane, easily the best AI product out there, and it is free to use. The new Mindmap feature makes learning so easy. You can use it to understand your codebase. Just convert your codebase to a single file and try it out.

Google NotebookLM is absolutely insane, easily the best AI product out there, and it is free to use. The new Mindmap feature makes learning so easy. You can use it to understand your codebase. Just convert your codebase to a single file and try it out.

AshutoshShrivastava

240,949 次观看 • 1 年前

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. This is the application we all deserve (at least if you have macOS.) Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. Here is the idea: You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. It sees what you see. It works right where you are. That's pretty cool. Here are a couple of cool examples: • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: Thanks to the Omnipilot team for collaborating with me on this post!

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. This is the application we all deserve (at least if you have macOS.) Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. Here is the idea: You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. It sees what you see. It works right where you are. That's pretty cool. Here are a couple of cool examples: • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: Thanks to the Omnipilot team for collaborating with me on this post!

Santiago

72,306 次观看 • 2 年前

This is Nouns. A new type of brand. A movement. It's open source. There's no copyright. Anyone can use it and create with it, in any way they want. And if your idea is great, Nouns will fund you to do it. What will you build? ⌐◨-◨

nounish ⌐◨-◨

82,751 次观看 • 3 年前

President Trump: “Spain said we can’t use their bases — We can use their bases. If we want, we can just fly in and use it. Nobody’s gonna tell us not to use it, but we don’t have to… Spain has absolutely nothing that we need other than great people — So we're gonna cut off all trade with Spain, we don't want anything to do with Spain."

President Trump: “Spain said we can’t use their bases — We can use their bases. If we want, we can just fly in and use it. Nobody’s gonna tell us not to use it, but we don’t have to… Spain has absolutely nothing that we need other than great people — So we're gonna cut off all trade with Spain, we don't want anything to do with Spain."

MJTruthUltra

63,656 次观看 • 7 个月前

🚨 Secure OpenClaw - Message Your Custom AI Agent From Telegram We are excited for our first release of personal agents. You can now use Abacus AI's DeepAgent to vibe code a personal agent on Telegram Create and simply message the agent! - do tasks like respond to emails - schedule meetings - use the browser to book tickets - connect to your internal systems The agent runs on a secure environment with constraints and you can pretty much customize it exactly like you want it when you are building it This is just v1 - we are going to be launching something WAY more exciting soon

🚨 Secure OpenClaw - Message Your Custom AI Agent From Telegram We are excited for our first release of personal agents. You can now use Abacus AI's DeepAgent to vibe code a personal agent on Telegram Create and simply message the agent! - do tasks like respond to emails - schedule meetings - use the browser to book tickets - connect to your internal systems The agent runs on a secure environment with constraints and you can pretty much customize it exactly like you want it when you are building it This is just v1 - we are going to be launching something WAY more exciting soon

Bindu Reddy

10,702 次观看 • 7 个月前

I LOVE SOULSEEK. So I built a modern client and if you love soulseek and want to use it I'd love to share it with you. You can watch this video to get a quick feel but it's designed to be lightweight/simple and easy to browse users collections. That way you can find good new music and then buy that music and more on Bandcamp. If you'd like to use it just reply here and I'll dm you a link.

I LOVE SOULSEEK. So I built a modern client and if you love soulseek and want to use it I'd love to share it with you. You can watch this video to get a quick feel but it's designed to be lightweight/simple and easy to browse users collections. That way you can find good new music and then buy that music and more on Bandcamp. If you'd like to use it just reply here and I'll dm you a link.

Trev🙃r

218,054 次观看 • 8 个月前

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

21,079 次观看 • 1 个月前

Introducing Open Source AI CRM, that runs on your OpenClaw. A few weeks ago, we launched Ironclaw (An Open Source OpenClaw CRM Framework) which now has around 1.4k stars. A lot of people confused us with NearAI’s Ironclaw, so we changed our name to DenchClaw. OpenClaw today feels a lot like early React: the primitive is incredibly powerful, but the patterns are still forming, and everyone is piecing together their own way to actually use it. What made React explode wasn’t just React itself, but the emergence of frameworks like Gatsby and Next.js that turned raw capability into something opinionated, repeatable, and easy to adopt. That is how I think about DenchClaw. We are not just building on top of OpenClaw; we are trying to make it one of the clearest, most practical, and most complete ways to use OpenClaw in the real world. We are an OpenClaw Framework, we are aiming to be the most correct way to use OpenClaw. We entered Y Combinator with Merse (AI Audio Comic), it was an app that I personally never used. Michael Seibel confronted us on it, and said, “if you aren’t the best user of your consumer app, then who is?”. I now use DenchClaw daily for everything I do, it also works as a coding agent like Cursor, DenchClaw built DenchClaw. I am addicted to DenchClaw now that I can ask it, “hey in the companies table only show me the ones who have more than 5 employees” and it updates it live than me having to manually add a filter. On Dench, everything sits in a file system, the table filters, views, column toggles, calendar/gantt views, etc, so OpenClaw can directly work with it using Dench’s CRM skill. The CRM is built on top of DuckDB, the smallest, most performant and at the same time also feature rich database we could find. It creates a new OpenClaw🦞 profile called “dench”, and opens a new OpenClaw Gateway… that means you can run all your usual openclaw commands by just prefixing every command with `openclaw --profile dench` . It will start your gateway on port 19001 range. You will be able to access the DenchClaw frontend at localhost:3100. Once you open it on Safari, just add it to your Dock to use it as a PWA. Think of it as Cursor for your Mac which is based on OpenClaw. DenchClaw has a file tree view for you to use it as an elevated finder tool to do anything on your mac. I use it to create slides, do LinkedIn outreach using MY browser. DenchClaw sees what you see, does what you do. It’s the everything app, that sits locally on your mac. All yours. Just ask it “hey import my notion”, “hey import everything from my hubspot”, and it will literally go into your browser, export all objects and documents and put it in its own workspace that you can use. P.S. It comes with Garry Tan's GStack built in.

Mark Rachapoom

19,613 次观看 • 6 个月前

PayBox is for doers from your phone, at your desk, on the go it's free, easy to use, and works on any device we built the technology that actually lets your AI Agents spend money and act on your behalf you earned it, big dog

PayBox is for doers from your phone, at your desk, on the go it's free, easy to use, and works on any device we built the technology that actually lets your AI Agents spend money and act on your behalf you earned it, big dog

MoonPay 🟣

34,575 次观看 • 25 天前

[Jae was learning more about the BDS Movement] *he was listening to Hasan talking about the BDS List* 👨🏻‍🚀: What is the BDS List? Is that the boycotting list? I don't know there was an official one. I need to look it up. I've just been avoiding all products that like I'm associated. 👨🏻‍🚀: *looking through the list* Intel?? wait? Wait? Intel?? Wait guys, that means we literally can't use our computers. That's everybody. Wait, Dell, Intel, Chevron, HP. I don't use any of these. Disney. Disney?? You can't Microsoft? Wait, don't we- aren't we, aren't we all using Windows Microsoft? And Google? 💬: You can use it just don't buy more products if you can 💬: But the point is to no longer purchase 👨🏻‍🚀: Oh no longer purchase, ok I'm down! 👨🏻‍🚀: Wait Amazon?? Amazon?? So, we can't use Amazon anymore?? What do you use? 💬: yea some of them are just try not to use if you can but some of them are more targetted 💬: you got to focus on the ones you can actually do 👨🏻‍🚀: Like the priority boycott list? I see. I don't have to use any of those. The only things that I use here are Google, Amazon and that's about it. Yeah I don't use anything for Disney. So~ The man who's ever so willingly to learn more :')

[Jae was learning more about the BDS Movement] he was listening to Hasan talking about the BDS List 👨🏻‍🚀: What is the BDS List? Is that the boycotting list? I don't know there was an official one. I need to look it up. I've just been avoiding all products that like I'm associated. 👨🏻‍🚀: looking through the list Intel?? wait? Wait? Intel?? Wait guys, that means we literally can't use our computers. That's everybody. Wait, Dell, Intel, Chevron, HP. I don't use any of these. Disney. Disney?? You can't Microsoft? Wait, don't we- aren't we, aren't we all using Windows Microsoft? And Google? 💬: You can use it just don't buy more products if you can 💬: But the point is to no longer purchase 👨🏻‍🚀: Oh no longer purchase, ok I'm down! 👨🏻‍🚀: Wait Amazon?? Amazon?? So, we can't use Amazon anymore?? What do you use? 💬: yea some of them are just try not to use if you can but some of them are more targetted 💬: you got to focus on the ones you can actually do 👨🏻‍🚀: Like the priority boycott list? I see. I don't have to use any of those. The only things that I use here are Google, Amazon and that's about it. Yeah I don't use anything for Disney. So~ The man who's ever so willingly to learn more :')

nad

36,904 次观看 • 1 年前

We built TasteSkill to help people create better frontends with AI. Today we're introducing TasteCode A desktop app for your coding agents, with a dedicated Design Mode that avoids slop and instead produces good UI It is opensource and you can use it with your existing AI subscriptions!

We built TasteSkill to help people create better frontends with AI. Today we're introducing TasteCode A desktop app for your coding agents, with a dedicated Design Mode that avoids slop and instead produces good UI It is opensource and you can use it with your existing AI subscriptions!

Leon Lin

122,333 次观看 • 11 天前