
完整作品展
技术栈
60 projects


通过 GitMission 的交互式任务和浏览器终端与虚拟团队学习 Git。
@0shuvo0 · X

用 markdown 笔记组织想法,支持进度追踪,并将其可视化为交互式思维导图
@vasanthadabala · X
Not really a startup. It's just something I built for myself a simple note taking app with a planner, progress tracker, and mind map I'm going to share it publicly @NodesMap check it

使用 NASA 数据和 AI 占星术生成您的个性化星盘。
cosmogram · Product Hunt
www.cosmo-gram.com Astrology & AI


通过模拟和物流分析 FIFA World Cup 2026 小组赛难度。
@pgardunoc · X
I vibe coded this for the World Cup, and other projects

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.

实时地图应用,帮助分布式团队查看彼此的位置和时区。
@kapxapot · X
Okay... Connect me with my customers!

用 FieldCam 整理工地照片和视频,添加 GPS 和时间戳,自动生成 PDF 报告。
@12squaredAI · X
| @fieldcam_app

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

探索160个Three.js示例集合,了解3D网络图形和WebGL技术。
@maxchu2021 · X
160 Three.js examples built with Claude through vibe coding. AI didn’t replace coding—it accelerated experimentation and iteration. Next step: turning these demos into production-ready products. Link: #ThreeJS #WebGL #AI #Claude #VibeCoding

实时交互式天气雷达仪表板,显示大气层、热量等高线和风暴追踪。
@ebrahim_dev3 · X
An interactive, high-contrast weather radar application. The system provides real-time atmospheric visual layers over high-resolution satellite imagery with distinct airflow, thermal contours, and storm tracks.