完整作品展
技术栈
23 projects
为任何事物投票排名，让网络决定什么最好。
@abenzick · X
This weekend I vibe coded a new website: live rankings of anything and everything. Want to know the best slice of pizza in Dallas? Want to vote for the greatest band of all time? Is Tom Brady the greatest quarterback? You vote, the internet decides.
在多种格式中与AI进行实时辩论练习，获得性能反馈。
@prof_safezone · X
Gambling on debate rounds with AI judges.
为创意团队打造的AI视频和图像审阅工具，支持自动转录和像素级评论。
@codesharpdev · X
《八仙！》影迷资料库，含角色资料、性格测试和社区评论。
marcushuang4595 · V2EX
给《八仙！》做了个非官方影迷资料站，顺便实践中文内容 SEO 最近关注到动画电影《八仙！》，发现上映信息、角色资料和传统传说容易混在一起，于是做了一个非官方中文影迷站： https://baxianwiki.com/?utm_source=v2ex&utm_medium=community&utm_campaign=launch 目前做了这些内容： - 上映时间、片长、儿童观影建议等观影指南 - 八位角色资料页，以及电影设定/传统原型的明确区分 - 人物关系页、电影与传统传说对照页 - “你是哪位八仙”性格测试和八仙知识挑战 - 基于 Redis 的观后感区，支持评分和剧透折叠 - sitemap 、robots 、结构化数据、移动端适配和内容型内链 技术上是 App Router 风格项目，经 Vinext/Nitro 输出到 Vercel ，论坛数据放在 Redis 。页面主要面向国内移动端访问，所以在视觉、首屏信息密度和交互尺寸上做了针对性调整。 这个项目主要是练习中文内容站、长尾关键词页面和轻交互，不准备做盗版下载或激进变现。网站也明确标
连接 Strava、WHOOP 和 Garmin 的 AI 教练，提供个性化训练指导。
daniel_s · HN
My triathlon coach (not a human) now texts me on iMessage
60+破冰游戏，配套宾果卡和队名生成器，无需注册。
Icebreaker Games — 破冰游戏：搜索、筛选、按步骤直接开玩。
通过类似人类管理方式的界面来管理多个AI agent团队。
jackcollinshq · Product Hunt
YAGNI Proactive agent teams you manage like humans
管理学术会议：提交和审阅论文、处理日程安排和注册。
@harryjwang · X
I've used many of the major conference systems. Plenty still have docs as an unsearchable static site — or worse, as PDFs that stopped tracking the product three versions ago. Somehow, still true in 2026. We took an AI-first path with instead. Our docs are generated from the codebase itself. A custom Claude Code skill writes each page and retakes the screenshots whenever a feature changes — so the docs don't drift from the product. Every page still gets reviewed by a human before it ships. Now you can talk to them, too. We just shipped "Ask AI" over our docs: This feature also turned out to be a nice teaching case for agentic RAG vs. classic RAG: • Classic RAG: chunk → embed → vector DB → retrieve once, by fixed rules • Agentic RAG: hand the model a search tool and let it drive — write a query, read the results, rewrite, retry At more than 100 pages, still no vector database needed. And every answer cites the exact page it came from. #Age
