
完整作品展
技术栈
60 projects


React 和 shadcn/ui components,用于在营销和登陆页面上创建 animated visual elements
@pixelcave_john · X
Hey Germán! I recently launched and a major update to Tailkit!

可视化构建和部署企业级 Next.js 应用的平台。
@sivasankar___s · X
I’m currently deep in building Rudra, a visual orchestrator for Next.js designed for full engineering control. Zero vendor lock-in—you own the code. Website: App Build with Rudra

在请AI修改代码前,先理解代码流程和应用连接。
@minmuner_devlog · X
Thanks for the feedback; I’m open to anything.

通过可视化、感知来源的新闻地图探索全球事件。
@brryg_ · X
sure man, working on a social and visual news hub called heuron - lmk what you think!


输入旅游地点即可生成旅行地图动画视频,无需学习复杂工具。
@yan_ianthe · X
Shoutout to travelboast and — gorgeous travel map animations. I just wanted one for my own trip without learning a timeline. so with GPT 5.5 vibe coding I shipped ✨Free, browser-only, no login, type your stops → get a video. this is what "vibe coding a weekend project" actually looks like: no spec, no figma, just "build me X" in a chat window.


用AI自动将设计图转换成可用代码。
@AnimaApp · X
Image to code in 1 minute - 20x faster than Claude Code and with much higher fidelity. Try it at and let us know how we did 🤘

在全球交互式地图上发现初创创始人、独立黑客和 SaaS 构建者。
@CiprianiRanieri · X
Builders Map: community of builders from all over the world.

Jiki 通过编码游戏和挑战学习编程基础,适合 LLM 时代
@RahimNathwani · X
Not a direct answer but the guys at Exercism (non-profit that publishes really good and free programming language self-study courses) recently launched a separate site to teach junior programmers both vibe coding and software engineering fundamentals.

Flint是为AI代理设计的可视化语言,用于创建交互式数据可视化。
chenglong-hn · HN
Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple