
Pengin AI — Browser-Native AI SDK
Run AI models in users' browsers with one script tag, no server or API key needed.
@erdemwrites · X
The full gallery
Tech stack
60 projects

Run AI models in users' browsers with one script tag, no server or API key needed.
@erdemwrites · X

Browse parametric visual effects, tune them live in the browser, and export compiling source for SwiftUI, React Native, and the web.
@dotvonesy · X
Beautiful Effects for Mobile and Web:

Interactive React parallax component with scroll and pointer motion effects, zero dependencies.
@iampoul · X
made with v0 and just a fun demo to try my own parallax package xD got bored.

Capture UI elements with code context and screenshots to share with AI agents for debugging visual bugs.
Loerei · HN
I found that describing where a broken UI is and taking screenshots for AI agents really sucks. I’m too lazy to explain an indescribable visual bug or capture a millisecond-long flash. I also don’t want to remember which file defines an element, whether it's right in the .tsx or a problem with the Parent Styles in .css. And even if you can point out the exact file, your agent still has to dig through thousands of lines of code to know what on earth you're yapping about. In a 7700-file monorepo like Cal.com, simply giving the right file in the prompt for your agent saves about 68.9% of execution time and 94.2% of the tokens your agent needs to digest. HoverSource gives all the needed information and further pushes it to -88.5% time and -94.5% tokens, basically skipping the entire digging session and jumping straight to reasoning and executing. The save is linear to how big your codebase is. I want to save tokens, but don’t want to spend my time and energy digging manually, and a junio

Free React component library with 80+ glassmorphic designs for Next.js and Tailwind CSS.
@AdeebMirza83 · X
🚀 I just shipped IntelliHelper UI — my Liquid Glass React component library. Try it: GitHub: 80+ components. 5 gorgeous themes. CLI installs in seconds. Frosted chrome that stays quiet. Expressive content panels that pop. Built for Next.js + Tailwind, copy-paste ownership like shadcn, but with a stunning glass design system that feels premium. And yes — official plugins & MCP so Claude, Grok, Cursor & agents actually understand how to use it. Live previews, full source, open source (MIT). What do you think of the glass effect? 👇 Drop your feedback — building in public starts now! #React #NextJS #Tailwind #UI #OpenSource #WebDev #DesignSystem

Merge images and PDFs into high-quality documents in your browser, with no uploads or accounts.
@_AayushTripathi · X

Local-first workspace for authoring, previewing, and exporting design systems.
@ricouii · X
我已经围绕 design.md 做了一个开源的工作台,以及品牌库 工作台支持模板编辑、预览、AI 生成、文件派生 token、css,品牌库方面还支持 HTML preview... 我还是相信 design md 是很有潜力的,比大部分的设计 skill 好用

Computational whiteboard for data analysis and insights, no signup required.
tccole · HN
Napkinbook, a smart canvas for discovering, and sharing insights

Design and deploy AI workflows and agents with a visual no-code builder.
@RanRan1357699 · X
Just shipped a smart guardrail in experiments: if your flow needs test data, it now blocks runs with a friendly prompt and offers one-click AI-generated samples. No more silent all-fail runs! Small details, big peace of mind. #BuildInPublic

A browser-based dev machine with shell, git, and local AI that collects no data.
Dhravya · GitHub
burrow a whole dev machine in a browser tab - bun.wasm, shell, git, and local AI. phones home to nobody.

AI-readable design context packs that help coding agents make better design decisions.
heywitt · HN
UnUI – Help coding agents make better design decisions

Design and export beautiful mesh gradients, waves, and patterns with GPU-accelerated effects.
@zoxilsi · X