Hacker News Reader

Very interesting.

I want to give it a try, but I see that one of the dependencies is "ollama" which is a Mac App and I don't have a Mac.

I'm running Llama models locally using llama-cpp-python which provides an OpenAI compatibility layer.

It should work on Linux and also with WSL. You could also try running it in Docker.

I see. Does ollama have an http API (this the curl requirement)? If so, is it compatible with OpenAI API?

Yes, it works with an Ollama server and the communication is done via HTTP. I know that someone configured my plugin to talk to OpenAI.

Oh, can install Ollama in Linux/WSL as well