stym06

You can already switch windows with cmd+~ button

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.

nice

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/

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.

How's it different from existing open source data catalogs like amundsen.io?

If a human had done this, these would be at a museum

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.

> "But I got it all working; now I can finally stop explaining to my boss why we need to re-structure the monitoring stack every year."

Prometheus and Grafana have been progressing in their own ways and each of them is trying to have a fullstack solution and then the OTEL thingy came and ruined the party for everyone

Still WIP, but the idea is to have a Grafana like setup for data quality

Absolutely loved your project ZoneTree. Gotta dig deep on this

I guess so! Will be fixed

Yet to implement linting and unit tests. This is kind of a rough draft/v0

Will do! Thanks for the comment

Thanks! Could you please point me to a reference for (1)

etcd/wal actually does do preallocations (https://github.com/etcd-io/etcd/blob/24e05998c68f481af2bd567...)

Yet to implement max buffer age! Any references for this would be bomb!

Is mmap() really needed here? Came across a similar project that does this? Really gotta dig deep here! https://github.com/jhunters/bigqueue

1. You're right! Will fix it to handle this as well as the support for relative directories

2. Yes, Will integrate a logging library instead of fmt (https://github.com/uber-go/zap)

OP here! Pls feel free to raise any bugs you encounter! I'll be doing the following immmediate fixes:

1. Use fsync for durable writes in case of system crashes

2. Fix log-rotation-purging logic

3. Fix `file already closed` bug on consecutive writes

4. Add CRC checksum

Thanks for your input @sakras. I'll fix this

Yes there are a lot of bugs since I just wrote this in one sitting today. Will be fixing all of this. For log rotation, I'll sort by the last_modified_at ts and then purge those

I used the bufio flush mechanism https://pkg.go.dev/bufio#Writer.Flush

Thanks for your comment, I'll definitely check it out. It was my first attempt at this. How can I make it better?

That sucks! Now I'm thinking my github action that is doing a `git pull repo && cd repo/ && rm -rf dist/ && populate.sh && git push` in my bash script will totally go rogue one day and kill everything. Any idea, peeps?

google might see this and add it as an offering with cost lower than bigtable

It's a 2018 piece.