[lgrammel]

I’m working on ModelFusion, a TypeScript library for working with AI models (llm, image, etc.)

https://github.com/lgrammel/modelfusion

It is only getting limited traction so I’m wondering if I’m missing something fundamental with the approach that I’m taking.

[gsuuon]

I had it starred! It looks like a nice set of tools for building a multi-modal AI app - I'll give it a try when I flesh out a discord AI gaming app I was working on. Is the multi-modal aspect (image, audio, language) the main focus? Maybe putting that a bit higher in the readme would help it stick - the intro section was a bit too dense and I ended up skimming it.

As for traction, I wonder if there just isn't much interest in AI with JS/TS right now, for whatever reason?

[lgrammel]

Yes, good point, JS/TS is definitely behind Python. That might explain some of it.

I expect most models to become multi modal in the future and am building towards. A lot of the core logic of agents will nevertheless be text based imo, so that’s a central piece, but I already added text to image and speech to text, and plan to add text to speech next.

[patwoz]

This looks awesome! Keep sharing. I think many newbies are looking exactly for something like that including me to get startet with AI :)

[lgrammel]

Thanks :) I’ll post here when I have larger updates.