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 TasteCode A few months, when we released TasteSkill, we wanted to fix frontend issues with models. With TasteCode, we’re moving closer to AI making great, production-ready design. Its an open-source ADE, focused on great design and UX, being easy to use, and the best - our design agent.... show more

bluedev

3,071 subscribers

43,722 次观看 • 2 天前 •via X (Twitter)

艺术科学技术

Anya Rossi• Live Now

Private livecam show

33 条评论

bluedev 的头像

bluedev2 天前

This website was made with Astra using TasteCode Design Agent, one-shot: We will keep improving the Design Agent. It's still a beta version, so expect it to get better with every update!

bluedev 的头像

bluedev2 天前

TasteCode is our submission to Product Hunt x OpenAI Astra Challenge If you want to help us, upvote here: GitHub, contributions welcome!:

Blckgenesiz 的头像

Blckgenesiz2 天前

Hmm the demo design isn’t really that impressive to be honest but I will give it a try.

zuno~ 的头像

zuno~2 天前

LETS GIOO

decipherx 的头像

decipherx2 天前

open source means the design agent can finally be judged on its worst page, not its demo page. i want to see the same ugly settings form attempted across codex, claude and grok.

Mason 的头像

Mason1 天前

This feels like Cursor but with the Codex agent, (amazing design)

y_qecea 的头像

y_qecea2 天前

Linux when

Ziwen 的头像

Ziwen2 天前

Good job!

Quoc Huy 的头像

Quoc Huy2 天前

Looks like it tastes nice

Clément 的头像

Clément1 天前

Is it kinda like Conductor?

omni 的头像

omni2 天前

This is so cool well done guys! I’m not sure if there already is but i would love to see taste skills for things that aren’t landing pages, maybe more specialised for documentation, dashboards etc.

Harshit Sehgal 的头像

Harshit Sehgal2 天前

Can you post some of the things you made with this, really interested and wanna see

Salise 的头像

Salise2 天前

cool that it supports Codex and Claude. makes it easier to integrate with existing tools.

J A Z I I 的头像

J A Z I I2 天前

Let's goooo

moku 的头像

moku2 天前

insane bro 👌🏼👌🏼

Nick 的头像

Nick2 天前

Congrats!🔥🔥

Luneri 的头像

Luneri2 天前

Fire

Arsh - 16 y/o builder 的头像

Arsh - 16 y/o builder1 天前

open sourcing the design agent is the interesting part. every closed one converges to the same generic landing page

Tereza Tizkova 的头像

Tereza Tizkova2 天前

When does it support @droid 👀

安叫兽|Bird🕊️ 🔶 BNB 的头像

安叫兽|Bird🕊️ 🔶 BNB2 天前

设计代理这块挺期待，前端终于不只是“能跑就行”了。

Ishu Agrawal 的头像

Ishu Agrawal2 天前

been waiting for this

Aryan 的头像

Aryan2 天前

Unable to connect the grok acc, it just goes to grok build website

Mira Takes 的头像

Mira Takes2 天前

The open-source ADE angle is compelling: model capability is becoming table stakes, while the workflow around taste, iteration, and UX is where the leverage compounds. Curious how you’re measuring “great design” across projects.

sebZsta 的头像

sebZsta2 天前

design taste is still the bit models fake. shipping something ugly teaches you faster.

The AI Therapist 的头像

The AI Therapist2 天前

TasteSkill fixed code. TasteCode fixes pixels. This is the $3B SaaS death spiral: you sell a wrapper to save devs 4 hours and they buy it for one week before realizing their design system already existed. Ship revenue, not features

mehdi 的头像

mehdi2 天前

Yo let’s go

Sweta 的头像

Sweta2 天前

How do users configure their existing model subscriptions within this open-source ADE?

Shay Ben Shabtay 的头像

Shay Ben Shabtay2 天前

Really cool and have a good launch even though competing now (in the astra challange)

remakw 的头像

remakw2 天前

W!!!

Byte 的头像

Byte1 天前

@blueemi99 welp gotta try it NOW. I have t3 code, monocode and zed delta. new one added to my collection

Rexx DZN 的头像

Rexx DZN2 天前

Hype

Hamza 的头像

Hamza2 天前

let’s go finally!!!

Rodrigo Yeo 的头像

Rodrigo Yeo1 天前

Great!!! I’ll try it today and give feedback later

相关视频

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

106,814 次观看 • 2 天前

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

James Rochabrun

61,608 次观看 • 3 个月前

We made Agent Design real before Claude Design became part of Claude Code. Open Design brings a live, editable artboard to any agent. Find it in the Codex Plugin Directory, or use the prompt below for Claude and other AI agents. ↘️

We made Agent Design real before Claude Design became part of Claude Code. Open Design brings a live, editable artboard to any agent. Find it in the Codex Plugin Directory, or use the prompt below for Claude and other AI agents. ↘️

OpenDesign

42,759 次观看 • 1 个月前

The most complete AI design skill stack is now in Open Design. AI agents can build full apps. But most of them still design like shit. You used to spend more time fixing the design than building the app. And prompting harder does not fix taste. So Open Design integrated the design skills everyone on X is talking about: Taste Skill Hallmark Frontend Design Image-to-Code Design Review 100+ design systems It works locally with 20+ AI CLIs: Codex, Claude Code, Cursor, Gemini CLI, OpenCode, and more. Pick your agent. Generate pages that finally have taste. 👉

The most complete AI design skill stack is now in Open Design. AI agents can build full apps. But most of them still design like shit. You used to spend more time fixing the design than building the app. And prompting harder does not fix taste. So Open Design integrated the design skills everyone on X is talking about: Taste Skill Hallmark Frontend Design Image-to-Code Design Review 100+ design systems It works locally with 20+ AI CLIs: Codex, Claude Code, Cursor, Gemini CLI, OpenCode, and more. Pick your agent. Generate pages that finally have taste. 👉

Open Design

53,135 次观看 • 3 个月前

Today we’re launching Design Canvas for AI agents. AI can build a feature, but every "design tweak" turns into another prompt. We built a drag & drop editor for Claude Code, Cursor, Codex to explore and iterate on your UI, so you get the best design by default. No endless prompting. Ship better designs in code with Subframe.

Today we’re launching Design Canvas for AI agents. AI can build a feature, but every "design tweak" turns into another prompt. We built a drag & drop editor for Claude Code, Cursor, Codex to explore and iterate on your UI, so you get the best design by default. No endless prompting. Ship better designs in code with Subframe.

Irvin Zhan

301,000 次观看 • 7 个月前

We raised $7.5M to kill AI slop. Introducing Moda: the world's first design agent with taste. RT+ comment “Moda” and we’ll design your brand for FREE.

Anvisha

4,539,773 次观看 • 5 个月前

Now you can use AI agents to design directly on the Figma canvas, with our new use_figma MCP tool and skills to teach them. Open beta starts today.

Now you can use AI agents to design directly on the Figma canvas, with our new use_figma MCP tool and skills to teach them. Open beta starts today.

Figma

17,869,312 次观看 • 5 个月前

Grok CLI >>> Cursor and Claude Code We wanted an IDE for xAI's Grok so we did something meta: we prompted the newly released Grok 4 to create... Grok CLI itself! Grok CLI can: 1. Modify local files and use the shell 2. Go through huge codebases and fix them 3. Persist for longer and solve really complex math and physics problems Instant setup on Replit ⠕ Bonus: Can create and run ai agents with it's completely open source!! link to the code: link to the repl:

Grok CLI >>> Cursor and Claude Code We wanted an IDE for xAI's Grok so we did something meta: we prompted the newly released Grok 4 to create... Grok CLI itself! Grok CLI can: 1. Modify local files and use the shell 2. Go through huge codebases and fix them 3. Persist for longer and solve really complex math and physics problems Instant setup on Replit ⠕ Bonus: Can create and run ai agents with it's completely open source!! link to the code: link to the repl:

Karan Vaidya

346,068 次观看 • 1 年前

🎨 Introducing Genspark Design The next-gen AI for design and creation, powered by Claude Opus 4.7. From rough idea to professional design, no design background needed. - One tool for everything you design. UI prototypes, videos, HTML animations, posters — all in one place and production-ready. - Stay on-brand with your own design system. Upload your Figma files or save your designs, reuse them across every project, and share them with your team. - Ship it, don't just mock it. Turn any app or website design into working code with one click, built on Genspark Code. Start building at our launch price 👉

Genspark

179,614 次观看 • 2 个月前

A toolkit for building agents that watch, listen, and understand video. Low latency by design. Open source. Production ready. Vision Agents lets you build real time video AI that works with your models and your edge layer. Supports YOLO, Moondream, Cartesia, Deepgram, ElevenLabs, HeyGen, Gemini, OpenAI, and more. Quick model switching. Easy to use API. Perfect for coaching tools, collaboration apps, avatars, and robotics.

A toolkit for building agents that watch, listen, and understand video. Low latency by design. Open source. Production ready. Vision Agents lets you build real time video AI that works with your models and your edge layer. Supports YOLO, Moondream, Cartesia, Deepgram, ElevenLabs, HeyGen, Gemini, OpenAI, and more. Quick model switching. Easy to use API. Perfect for coaching tools, collaboration apps, avatars, and robotics.

GitHub Projects Community

30,274 次观看 • 9 个月前

Introducing our Free Figma-to-Code converter. Copy your design directly from Figma and paste it into our canvas. Our compiler converts your figma design into code, and you can export it in your preferred format. Free to use, with no limits. No login required, try it here👇

Introducing our Free Figma-to-Code converter. Copy your design directly from Figma and paste it into our canvas. Our compiler converts your figma design into code, and you can export it in your preferred format. Free to use, with no limits. No login required, try it here👇

Praha

23,097 次观看 • 12 天前

With the stack fixed, can an AI agent choose data and experiment like a researcher? At Evolvent AI, we built RSIBench-Data to test whether agents can diagnose failures, design data, train checkpoints, and use feedback. 🧵 📄 💻

With the stack fixed, can an AI agent choose data and experiment like a researcher? At Evolvent AI, we built RSIBench-Data to test whether agents can diagnose failures, design data, train checkpoints, and use feedback. 🧵 📄 💻

Fanqing

51,339 次观看 • 1 个月前

Why we switched from Figma to Claude Design “I let the team do whatever is best for them, and this is a trend I've observed amongst almost everybody: Claude Design has done a great job. People really like using it, it's easy to use, and we've had a natural movement towards it. It's also easier to not manage too many tools and licenses. Because Claude keeps making all these great features, people just gravitate towards it, with less friction than having procurement issue Figma licenses for every single person.” To what extent do you think Claude Design cannibalises Figma Danny Trinh Siqi Chen Julie Zhuo Jackie Bavaro

Why we switched from Figma to Claude Design “I let the team do whatever is best for them, and this is a trend I've observed amongst almost everybody: Claude Design has done a great job. People really like using it, it's easy to use, and we've had a natural movement towards it. It's also easier to not manage too many tools and licenses. Because Claude keeps making all these great features, people just gravitate towards it, with less friction than having procurement issue Figma licenses for every single person.” To what extent do you think Claude Design cannibalises Figma Danny Trinh Siqi Chen Julie Zhuo Jackie Bavaro

Harry Stebbings

47,782 次观看 • 1 个月前

Figma Make, now on your local code In limited beta starting today, you can visually edit and ship changes by connecting Make to your codebase At Figma, we use our products to design in every way: design layers, prototypes, and now, production code

Figma Make, now on your local code In limited beta starting today, you can visually edit and ship changes by connecting Make to your codebase At Figma, we use our products to design in every way: design layers, prototypes, and now, production code

Figma

400,818 次观看 • 3 个月前

The DESIGN.md upgrade is officially live in Stitch! 🚀 Yesterday we open-sourced the spec, and today we are giving you more tools to use it: 📄 Start with DESIGN.md: Attach a DESIGN.md right at the start of a project. Don't have one? Our new wizard will help you extract one from your code base or the web. 🔄 DESIGN.md to Design System: Upload a DESIGN.md file to generate a Design System on the canvas. 🧩 Token Support: Design Systems now support design tokens from DESIGN.md! Add them to your file and Stitch will seamlessly incorporate them. 🗑️ Clean Up: (You asked, we listened) You can now easily delete a design system. We’re excited to build the open design standard together. 👇

The DESIGN.md upgrade is officially live in Stitch! 🚀 Yesterday we open-sourced the spec, and today we are giving you more tools to use it: 📄 Start with DESIGN.md: Attach a DESIGN.md right at the start of a project. Don't have one? Our new wizard will help you extract one from your code base or the web. 🔄 DESIGN.md to Design System: Upload a DESIGN.md file to generate a Design System on the canvas. 🧩 Token Support: Design Systems now support design tokens from DESIGN.md! Add them to your file and Stitch will seamlessly incorporate them. 🗑️ Clean Up: (You asked, we listened) You can now easily delete a design system. We’re excited to build the open design standard together. 👇

Stitch by Google

195,377 次观看 • 4 个月前

💡Can robots autonomously design their own tools and figure out how to use them? We present VLMgineer 🛠️, a framework that leverages Vision Language Models with Evolutionary Search to automatically generate and refine physical tool designs alongside corresponding robot action plans. ✨ VLMgineer can fully automate tool and action design with AI-driven physical creativity. No human intervention. No pre-defined templates or few-shot examples. ✨ VLMgineer outperforms human-specified designs and existing everyday tools. ✨ We let the VLM fully decide how to evolve designs. Deep dive with me: 🧵

💡Can robots autonomously design their own tools and figure out how to use them? We present VLMgineer 🛠️, a framework that leverages Vision Language Models with Evolutionary Search to automatically generate and refine physical tool designs alongside corresponding robot action plans. ✨ VLMgineer can fully automate tool and action design with AI-driven physical creativity. No human intervention. No pre-defined templates or few-shot examples. ✨ VLMgineer outperforms human-specified designs and existing everyday tools. ✨ We let the VLM fully decide how to evolve designs. Deep dive with me: 🧵

Junyao Shi

30,276 次观看 • 1 年前

Can Claude Code design proteins? We're just about to release our wet lab API + SDK so we made a quick demo to test how agents can interact with protein design models and submit the proteins to our lab for testing. This closes the loop between the computational design and the experiment validation We queued up a bunch of agent-designed proteins for wet lab validation, will release the results in a couple weeks on Proteinbase

Can Claude Code design proteins? We're just about to release our wet lab API + SDK so we made a quick demo to test how agents can interact with protein design models and submit the proteins to our lab for testing. This closes the loop between the computational design and the experiment validation We queued up a bunch of agent-designed proteins for wet lab validation, will release the results in a couple weeks on Proteinbase

Julian Englert

81,792 次观看 • 8 个月前

So which model is the best at frontend design? You can now eval pretty much all of them in pen(dot)dev in realtime in parallel. It's the most versatile design agent, where you can Sign in with ChatGPT, use your Claude subscription, OpenCode Go, Github CoPilot, connect Cursor Composer 2.5/Grok 4.5, Minimax M3, Kimi K2.7/K3, GLM 5.2, Gemini 3.5 Flash, Qwen 3.7 Plus etc, mix and match these models on design tasks directly in your codebase locally on your desktop.

So which model is the best at frontend design? You can now eval pretty much all of them in pen(dot)dev in realtime in parallel. It's the most versatile design agent, where you can Sign in with ChatGPT, use your Claude subscription, OpenCode Go, Github CoPilot, connect Cursor Composer 2.5/Grok 4.5, Minimax M3, Kimi K2.7/K3, GLM 5.2, Gemini 3.5 Flash, Qwen 3.7 Plus etc, mix and match these models on design tasks directly in your codebase locally on your desktop.

Tom Krcha

2,457,818 次观看 • 2 个月前

I built a *human* curated list of 67 design skills (DESIGN md) of popular UI styles that you can use with AI 💻 locally tested by humans with Opus 4.7 🎨 works with Google Stitch, Claude Design 🤖 supports SKILL md files too 💵 free and pro version also available You can also pair these with a collection of UI prompts to build hero, pricing, and feature sections from the TypeUI website 🙌

I built a human curated list of 67 design skills (DESIGN md) of popular UI styles that you can use with AI 💻 locally tested by humans with Opus 4.7 🎨 works with Google Stitch, Claude Design 🤖 supports SKILL md files too 💵 free and pro version also available You can also pair these with a collection of UI prompts to build hero, pricing, and feature sections from the TypeUI website 🙌

Zoltán Szőgyényi

28,239 次观看 • 4 个月前

Today we’re launching an experimental @Figma plugin that will convert your design into runnable code. Generate a Repl directly from Figma, and instantly share a static React app with your team. Then, use Replit AI to add functionality and get your code production-ready.

Today we’re launching an experimental @Figma plugin that will convert your design into runnable code. Generate a Repl directly from Figma, and instantly share a static React app with your team. Then, use Replit AI to add functionality and get your code production-ready.

Replit ⠕

524,579 次观看 • 2 年前