Much kudos. I hope more people discover how powerful even a local search index of previously visited content can be. And I hope more people can build large indexes as well, so we're not just relying on Brave & Mojeek & Marginalia (and EUSP) to rescue us for the fallback discovery searches.

There's also the cross conversation memory search, which uses a different conversation dataset (the Claude Web / Claude.AI conversations) than Claude Code does. I'm not even sure Claude Code does cross conversation search?

The Desktop interface also presents Markdown as formatted text and presents artifacts (especially interactive ones) better than the CLI can.

All that said - I actually use the CLI for nearly everything (even on Windows). Rather than use Claude Desktop for daily "routines" that are capped at 15 total cron-jobs and use extra usage credits, I think I'll continue building my own minimal harness and move my routines to models from other providers.

This is one of the first things I “fixed” with skills and hooks. I index every conversation in SQLite and have a skill which knows what to do when I ask it to search the index. I had to avoid the word memory because it’s too tied up in other parts of the context. It even indexes across my different machines. I set this up because I have terrible context discipline. I’ll go off on a tangent in one context and start planning and sometimes implementing something based on that thread which really deserves its own context. Afterward I can create the new context and move relevant bits to it, but I’d lose that initial starting conversation which inherently has more data than the summary in the new context.

I also use a few different related contexts. One where I’m building a game engine in zig and another talking about game ideas. There’s a lot of back and forth going on there which needs some shared context. I solve this with a combination of Claude.md references and that searchable session index.

Everything I do with scheduled tasks are just wired up with systemd and simple scripts. No LLM in the critical execution path. Again a skill tells CC how I manage those scheduled things so I just have to say something like “run this every day at midnight” and CC has reliably taken care of the rest.

It (Claude Code) does, I discovered it by accident recently, having never used daily routines before. Haven't touched Claude Desktop at all, outside of playing with it for 30 mins or so months ago.

TLDR: I used Claude Code to build a command that scrapes job postings from a few employers I am interested in (it is a bit more complicated than that, but that's the gist). At the end CC asked me "do you want me to re-run it daily?" I said yes, and it generated a daily routine and gave me a URL to my anthropic account page where I can see all my daily routines.

There, it says that I am currently using up 1 out of 15 "free" daily routines that come with my personal subscription, and I would have to pay extra if I want to have more than 15 active at a time (I assume by switching to per-token pricing for anything beyond 15, but not sure).

I also haven't touched routines, but I use cc to write automation tasks that will integrate a model when I need an inference layer. Which I also did before routines..

Have people actually been using routines effectively?

I think this would be a very useful feature to add to HN itself. I nearly emailed dang a few weeks ago to suggest it myself rather than roll my own browser extension to do it, though maybe it's my own responsibility to roll my own software too.

The Gearspace forums (vBulletin based?) have an "Ignore User" feature that helps make that forum vastly more tolerable.

You do know Eurovision Asia begins this November and was announced as part of the telecast? And that Canada is expected to be part of Eurovision next year?

(Yes, I do know you were making a joke and don't particularly care! ;) )

There's also the geopolitical issues, which I'll skip over because similar concerns can be leveled at other indexes too. I posted about that on the Kagi feedback forums back in 2024:

https://kagifeedback.org/d/4727-option-to-choose-or-exclude-...

I since built my own metasearch engine for my own use, where I choose the external indexes used, and I'm much happier. I started building a personal index of the web as well. I haven't used Kagi or Google for over a year now.

I hope I'm not distracting from Bruno's Uruky project here. Not everyone is technical enough to spin up some PHP code and make their own metasearch, or spin up a VPS and install a SearxNG instance. There's value in providing a good user experience for less technical users, in building resilience by using multiple indexes & building your own, and reducing dependencies on external index APIs that may cut off your access (coffgooglebingcoff). I'm glad services like Uruky exist.

I'm only paying Mojeek about $10 - $20 per year in API for my personal metasearch, so I guess this is a terrible market to enter ;) But I'd genuinely be interested, especially if the money is going towards building an index.

I'd recommend you look into any of our other search providers if you just want the API search!

It would be nice to have more search indexes available though, especially via APIs.

I wish Kagi was a search index, back when I was a Kagi subscriber that's what I hoped my funds were going towards building.