Hacker News Reader

They default it to talking to a free version of their model (which is incredibly cheap if you decide you like it.)

But it seems trivially easy to run it against local models. Their onboarding guide offers that option, though I have no idea if it changes any functionality.

The latter. It looks like it's meant to be a batteries-included agent to promote their free-for-a-limited time AI service that it connects to by default.

Ok, fair enough compared to the rest of the proeminent actors I guess, but quite confusing from dev point of view. Lately I started to experiment with model like Qwen2.5 on local. Good enough to ask simple question, but didn’t manage to do anything remotely close a agents I started to experiment with through Copilot.

qwen3.5 9b runs okay on my 12GB gaming GPU. It's very stupid as a coding agent but it's possible to get useful work out of it.

I am experimenting with LFM2.5-8B-1A and getting 250tps on a 3060

It defaults to the API, but you can download the weights for the 1T-parameter Pro model and selfhost if you have the hardware for it.