Recent submissions

Comment · 1 month ago
You can already switch windows with cmd+~ button
Comment · 8 months ago
Hey HN, I built QuickGitHub.

The idea is simple: take any GitHub URL, add “quick” before github.com, and get AI-generated system design documentation in under 60 seconds.

github.com/vercel/next.js → quickgithub.com/vercel/next.js

The generated docs include a system overview, architecture breakdown, key modules, tech stack, entry points, and dependencies.

There’s also a Q&A chat to ask follow-up questions about the repo.

Why I built this:

I think we’re heading toward a world where most code is written by AI agents, and the bottleneck shifts from writing code to understanding what was written. Traditional docs assume a human author. I wanted something that could explain any codebase instantly, regardless of who (or what) wrote it.

Some details: * Each repo is indexed once and cached permanently * Login required via GitHub OAuth (one free repo per account) * All generated docs are public by default * It’s open source: github.com/stym06/quickgithub

Would love feedback on the quality of the generated docs.

Try it on a repo you know well and tell me where it gets things wrong. that’s the most useful feedback I can get.

Comment · 8 months ago
nice
Comment · 8 months ago
Introducing Kepler

An open-source text-to-SQL platform that lets you query data warehouses in plain English. It currently supports ClickHouse.

https://github.com/stym06/kepler

1. Ask a question in natural language 2. Kepler finds relevant tables and recalls past learnings 3. The AI agent generates SQL, executes it read-only, and validates results 4. Results appear with suggested charts when appropriate

It features persistent memory - it learns corrections, schema notes, and patterns across sessions, implemented using Qdrant + Ollama (nomic-embed-text).

Based on a recent research paper published by OpenAI https://openai.com/index/inside-our-in-house-data-agent/

Comment · 11 months ago
you could just rank the papers, and show trending ones as a separate tab.

for filters, create a set of pre-defined tags and let the LLM choose one of your pre-defined tags from the paper's summary.

Comment · 11 months ago
How's it different from existing open source data catalogs like amundsen.io?
Comment · 11 months ago
If a human had done this, these would be at a museum
Comment · 11 months ago
off topic, but prometheus pushgateway is such a bad implementation (once you push the metrics, it always stays there until it's restarted, like counter does not increase, it just pushes a new metric with the new value) that we had to write our own metrics collector endpoint.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton