Go to the "Cost" -> "Intelligence Index vs. Cost per Intelligence Index Task" That diagram maps their "Intelligence" score to "cost per task" and I think this gives a good basis on deciding with which model you want to go. Then you can either get an API token from that models provider directly or use openrouter and set openrouter to the model/providers of your choice.

You can also see on openrouter itself the details for each model like prices and what providers are offering it at what price.

Finally you can compare models details using openrouters compare feature like this:

https://openrouter.ai/compare/anthropic/claude-opus-5.5/open...

Latest feature is the ability to share custom monsters with the community so they can be used by others in their own encounters.

The user numbers are climbing slowly but steadily without me doing much if any promo. I think this is actually pretty good since it gives me the chance to expand functionality slowly while a few people are actively "testing" the site.

Maybe at some point I will need to do some more promotional work though even though I am not sure how yet :P

I am using a locally hosted version of https://github.com/booklore-app/booklore which supports OPDS protocol. KOReader can then directly connect to that booklore server and you browse your library and download what you want. It is not the best UX ever but it works :)

But I was also wondering, how this even works. The AI agent can have its own cursors and none of its actions interrupt my own workflow at all? Maybe I need to try this.

Also, this sounds like it would be very expensive since from my understanding each app frame needs to be analysed as an image first, which is pretty token intensive.

For those DMs that use tools like these, my app sits between Shieldmaiden and Improved Initiative in terms of features/complexity. I tried to offer as many features as possible but "hide" them in a way that makes it easy to understand the most important information like initiative order, health and conditions, stat-blocks. But then I added many buttons with keyboard shortcuts and a quick-access command-palette (think MacOS Spotlight or Alfred on Linux) that lets you access even more commands and features just by typing.

It is in beta, free and and you can check it out at https://topoftheround.com

I tried to make it very easy to use by offering keyboard shortcuts for all important actions. I think it can be used by just keyboard alone. It also has a command-palette like MacOS or Alfred on linux (shortcut is "/") that lets you search for all important commands and even glossary entries.

There is a "Demo mode" that shows an example encounter and guides you through the basic functions. If anyone wants to check it out and tell me if this is understandable or if I need to add more/better tutorial steps? That would be great :)

It is build with javascrpit/typescript and uses Firebase/Firestore.

Any DMs on here that want to give this a try?

Comments URL: https://news.ycombinator.com/item?id=47611374

Points: 1

# Comments: 0

I think the experimental Docker Ai Sandboxes do this as well: https://docs.docker.com/ai/sandboxes/ Plus free choice of inference model.

It looks like the remote has volume buttons on the right side by the way.