
openstem — code skills that finally stick
Learn code skills with flashcards, quizzes, and AI tutoring built on memory science.
@mkappworks · X
I am building lets connect
The full gallery
Tech stack
20 projects

Learn code skills with flashcards, quizzes, and AI tutoring built on memory science.
@mkappworks · X
I am building lets connect

Log your daily experiences to build a record for neurodivergent diagnostic assessments.
@MathewsMat19207 · X

Train your concentration with interactive games including Schulte Tables, Stroop Tests, and reaction time challenges.
Focus Game — 专注力训练小游戏集合,包含 Schulte Table、Stroop Test、Reaction Time Test 等浏览器训练工具

Practice PTE Core with AI-scored questions and instant feedback.
phrasel_service · Product Hunt
Phrasel AI-powered PTE Core practice, feedback, and mock tests

Add timestamped questions and polls to videos to create interactive learning experiences.
@josephnordqvist · X

Personalized learning, ACT/SAT prep, essay support, and audio tutoring in 100+ languages.
@vrajshroff · X
Personalized learning for students

Upload class notes and generate exam questions, answers, and revision materials instantly.
@herogaming7358 · X
🚀 Finally shipped my first SaaS project! Introducing ExamPrepAI 📚 Turn your own PDF or image notes into: ✅ Important Questions ✅ Short Answers ✅ Revision Notes No fake promises. Just a smarter way to revise. 🌐 🎥 Tutorial:

Manage academic conferences: submit and review papers, handle scheduling and registration.
@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