
Thinking orbs — Animated thinking orb component
AI 和代理界面的动画思考球,六个精心调校的状态和自动明暗主题。
@MengTo · X
These will instantly make your vibe-coded projects look less generic. Free, open-source libraries from the same creator: • • •
完整作品展
技术栈
60 projects

AI 和代理界面的动画思考球,六个精心调校的状态和自动明暗主题。
@MengTo · X
These will instantly make your vibe-coded projects look less generic. Free, open-source libraries from the same creator: • • •

用相机捕捉颜色,创建调色板和渐变,编辑十六进制、RGB 和 CMYK 值。
@SwapnanilDhol · X
Uploading a new version of my first app ( to the App Store tomorrow built in-part with Codex!


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

通过可视化图表和代码界面创建GPU加速的视频效果和动态图形。
LOVELYZOMBIEYHO

上传产品图片,选择场景,AI生成专业级摄影照片。
@aftertakenai · X
for AI e-commerce product photography

探索数学曲线、分形、对称和拓扑的交互式可视化。
@vkuoo · X
Added more demos showcasing graph-math relationships, built with Codex.

在浏览器中将照片和视频转换为ASCII艺术、像素艺术和马赛克。
@kail_designs · X
Jokes aside but honestly (Landing page) was built with Claude (Opus 4.7) in 1 day. But no, it was not just four prompts or some random skills. Here's how I built the entire AsciiMagic landing page with Claude in one day👇 Started with a rough sketched wireframe. Then designed it in @paper Then I used the Paper MCP with Claude to recreate that design in code and get a solid first version running. From there, the real work began. I kept iterating with specialised Claude skills: • impeccable • frontend-design • emil-design-eng • review-animations • responsive-design • seo-audit Each one improved a different part of the experience. By the end, the page had: • Mobile-first responsiveness • Better SEO optimised copy • Smooth micro-interactions • Cleaner frontend architecture Then came the part people don't see. For the next 5–6 hours, I wasn't asking Claude to "make it prettier." I was: • Fine-tuning layouts • Uploading and compressing assets • Moving files across diff

上传PDF和视频创建视觉知识地图,使用AI研究助手进行对话。
allybahaei · HN
Bring all your sources into a visual space, ask questions with full context, branch LLM conversations, and go deep on YouTube videos / research papers to build your knowledge canvas.

Three.js打造的交互式3D圆柱形画廊,可拖动浏览
@kurichans_1996 · X
Cylindrical gallery built with @threejs 🤖 Generated with Claude Code Opus 4.7 demo:

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!
PixelFlow Create Pixel art, Pixel Animations, Music & SFX , 3d Worlds , 3d Voxel painting, Asset Generation and much more!
@Neuorix · X