Linkwise: AI read-later and knowledge app with curated Discover feed
Linkwise is an AI-powered read-later and knowledge app that helps users save and organize articles, essays, and videos. It features a curated Discover feed of high-quality content, built using Next.js with ISR, Supabase/Postgres, and Fable 5 for page generation. The app solves the problem of information overload by surfacing worthwhile reads.
Visit project ↗Entities
Related
Linkwise: AI read-later and knowledge app with curated Discover feed
Linkwise is an AI-powered read-later and knowledge app that helps users save and organize articles, essays, videos, and highlights. It features a curated public feed called Discover, generated using Fable 5, which selects content worth reading. The app solves information overload for knowledge workers and avid readers.
AI news aggregator agent that filters and summarizes
An agent that automatically collects AI news from multiple sources, filters out noise, and provides concise summaries. It uses LLMs to understand user interests and generate personalized digests, saving time for professionals who need to stay informed without constant scrolling.
AI generates learning roadmaps with prerequisite links
Clew is a learning app that uses LLMs to generate topic maps from a single prompt. It creates 100+ topics and prerequisite links, allowing users to explore subjects or learning goals interactively. The app solves the problem of manually creating study roadmaps for any subject.
AgainPage: daily digest from your markdown notes using LLMs
AgainPage is a desktop app that reads your local markdown notes, identifies themes and connections, and each morning generates a short newspaper-style edition that resurfaces forgotten notes and highlights links you missed. It solves the problem of never revisiting personal notes, using LLMs (local via Ollama or cloud API) to compose the digest.
LLM-powered learning tool that streams generated lessons to avoid user abandonment
A learning tool that generates personalized lessons from a user's profile using an LLM. The key insight was that streaming the lesson output (instead of showing a blank spinner during 50-second generation) dramatically improved user retention. Solves the problem of users assuming the app is broken when generation takes time.
