I see Jev as a major step towards commoditizing current LLM paradigm. One thing would be to further optimize this particular route to work purely on CPU. This will grant an option to embed this feature into any application, from MS Office to games. The other is integrating this into agent workflow to vastly minimize token consumption.

Also like to see a "layman harness" like LM Studio integrate an open decision model in its workflow.

Not in a serious manner but I created a testing harness for a Nintendo 3DS game I'm making that uses the OpenAI Decisions API. The main advantage is the speed (~2-300ms per input) which I really need for this purpose.

Not with Jev, but you can use classifiers for a lot of use cases, here’s a few: https://playground.jeffyclassify.com/

I use Jev in a Claude code hooks to detect dangerous commands.