HackerTrans
TopNewTrendsCommentsPastAskShowJobs

mihaela

no profile record

Submissions

[untitled]

1 points·by mihaela·पिछला माह·0 comments

[untitled]

1 points·by mihaela·4 माह पहले·0 comments

[untitled]

1 points·by mihaela·4 माह पहले·0 comments

Building MCP tools: AI agents read outputs every time, tool descriptions once

aleahim.com
1 points·by mihaela·7 माह पहले·0 comments

Show HN: Cupertino – MCP server giving Claude offline Apple documentation

aleahim.com
6 points·by mihaela·7 माह पहले·7 comments

Show HN: Cupertino – Offline Apple docs for AI agents (22K pages, MCP, Swift)

github.com
1 points·by mihaela·8 माह पहले·0 comments

comments

mihaela
·30 दिन पहले·discuss
Electron is no-platform. It is an insult to the user, and a lack of skill and effort for the developer. I'm currently using QT for Win and Linux, and Apple -tech for Apple.
mihaela
·5 माह पहले·discuss
Exactly. Shameful explanation.
mihaela
·5 माह पहले·discuss
I love Monodraw, and use it every week
mihaela
·7 माह पहले·discuss
Update: v0.3.0 shipped — setup is now 30 seconds

  The crawl time was the #1 friction point. Fixed it.

  cupertino setup now downloads pre-built databases from GitHub Releases. No more 20-hour crawls.

  138K+ docs pages and 606 sample projects, ready in under a minute.

  Blog post with details: https://aleahim.com/blog/cupertino-instant-setup/
mihaela
·7 माह पहले·discuss
Thanks! Let me know how it goes—happy to help if you hit any issues getting it set up.
mihaela
·7 माह पहले·discuss


  Update since launch:
  - 111k+ documentation pages indexed
  - 606 sample code projects (fully searchable)
  - Swift Evolution proposals, Swift.org docs, The Swift Book
  - Apple Archive legacy guides—deep conceptual docs for Core Animation, Core Graphics, Core Text, etc. that aren't in modern docs
  - 9,699 Swift packages cataloged

  Pre-built indexes available if you don't want to wait 20+ hours to crawl:
  - https://github.com/mihaelamj/cupertino-docs - Documentation archive
  - https://github.com/mihaelamj/cupertino-sample-code - Sample code mirror
mihaela
·7 माह पहले·discuss
Totally agree—ranking is both art and science. Beyond what I listed, I'm also penalizing nested types, boosting based on query patterns ("X protocol" → boost protocols), and inferring kind from URL depth when metadata is missing.

Still actively crawling docs (at 111k now) and vector/semantic search is on the roadmap.