完整作品展
技术栈
60 projects
InvoiceAI 用人工智能快速解析发票，帮助自由职业者和小企业提取关键信息。
@AmanSha72844101 · X
I have build an invoice parser tool for CA freelancer and small businesses and I build it with Cursor + Claude Those are my vibe coding tool not ____ you know Here is the link 👇
AI工具在90秒内通过财务分析和风险评估来压力测试商业创意。
@AIWMCX1 · X
Consultants don’t need more noise. AIWMC Quantis helps turn messy business ideas into clear scenarios, runway views, and risk signals — so you can spend less time rebuilding analysis and more time giving the client a real answer.
Autoppt是AI演示文稿生成工具，快速制作专业幻灯片。
Autoppt — AI 演示文稿生成工具，彻底改变了您创建演示文稿的方式。凭借丰富的模板和强大的功能，让您轻松在几分钟内制作出令人惊叹的演示文稿
使用 FRAI 扫描网站中的 AI 使用情况，并测试聊天机器人的偏差和安全性。
@sebuzdugan · X
building @getfrai , an open source toolkit that helps ML engineers navigate EU AI Act compliance, model cards, risk files, the boring but necessary stuff
从讲义、笔记或教科书图片生成结构化学习指南，附含关键概念和练习题。
@SundayEzek4130 · X
Still struggling with long lecture notes? Turn any difficult course into simple, easy-to-read notes in seconds. 🚀 Try it now: Check out what I just built with Lovable!
GuidedBase 将应用想法转化为蓝图和启动代码。
@GuidedBase · X
用 AI 分析 GitHub pull request 获得合并信心分数。
@aryawarti_aky · X
Hey Daniel ! I Built PRisk — an AI-powered pull request risk intelligence platform for GitHub & Gitea. Paste a PR URL and get an evidence-backed Merge Confidence Score before you merge. 🔗 I'd love to hear your feedback!
与神经网络互动，观察它如何识别手写数字。
mikky-a · HN
Living Neural Network on the Webpage
用AI从长视频自动生成短视频片段并导出为社交媒体格式。
@tryFrameOS · X
用于构建网站、编写代码和处理复杂任务的 Agentic AI 助手。
@durdom_evm · X
Chinese team at just dropped ZCode 3.0 and it's quietly reshaping the agentic coding landscape while everyone's waiting on Anthropic's roadmap here's what matters: GLM-5.2 is trading blows with Opus 4.8 on the benchmarks that actually count. 81.0 vs 85.0
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
AI Todo 用智能方式将目标分解为可行步骤，优化任务优先级。
AI Todo — 像很多程序员一样，我日常要兼顾工作任务、生活琐事、项目计划，时常感到事情多但漏掉的也不少。想用智能方式管理这些待办，但市面上的工具要么设计臃肿，要么 AI 能力很弱。于是我花了几周开发了 AI Todo，目标是:
