Show HN: HN Sieve – every Show HN scored and summarized by AI

HN Sieve launched as a tool that automatically discovers, analyzes and scores every Show HN submission on Hacker News using AI, evaluating each project on a 0-10 scale across Innovation, Technical Quality, Documentation and Utility. The system polls the Hacker News API every 2 minutes, fetches project content from URLs and GitHub repos, uses one LLM to triage whether a submission is a real project and a second LLM to score it and generate a summary, then indexes the results with embeddings for semantic search. Projects are classified into categories including devtools, ai-ml, web, infrastructure, security, data, mobile and developer-productivity, and users can submit any URL for instant evaluation or receive email digests of top new projects.

HN Sieve — AI-Curated Show HN Projects HN Sieve automatically discovers, analyzes, and scores every Show HN project on Hacker News using AI. Each project is evaluated across four dimensions — Innovation, Technical Quality, Documentation, and Utility — on a 0-10 scale, then categorized and made searchable. How it works 1. Collect — Polls the Hacker News API for new Show HN submissions every 2 minutes 2. Fetch — Retrieves project content from URLs, GitHub repos, landing pages 3. Classify — LLM-powered triage determines if the submission is a real project 4. Score — A second LLM evaluates across 4 dimensions and generates a summary 5. Index — Embeddings enable semantic search across all projects Features - Browse curated projects with filters by category, score, and time period - Semantic search — find projects by describing what you're looking for - Analyze any URL — submit a project for instant AI evaluation - Save projects to your personal collection - Email digests with top new projects - Full scoring breakdown: Innovation, Technical, Documentation, Utility Categories Projects are classified into: devtools, ai-ml, web, infrastructure, security, data, mobile, developer-productivity, and more. Browse all projects https://hnsieve.com