Preferences

This DevOps friction is exactly why I'm building an open-source "Firebase for LLMs." The moment you want to add AI to an app, you're forced to build a backend just to securely proxy API calls—you can't expose LLM API keys client-side. So developers who could previously build entire apps backend-free suddenly need servers, key management, rate limiting, logging, deployment... all just to make a single OpenAI call. Anyone else hit this wall? The gap between "AI-first" and "backend-free" development feels very solvable.

smpretzer
I think this lines up with Apple’s thesis of on-device models being a useful feature for developers who don’t want to deal with calling out the OpenAI

https://developer.apple.com/documentation/foundationmodels

sockboy
Yeah, hit this exact wall building a small AI tool. Ended up spinning up a whole backend just to keep the keys safe. Feels like there should be a simpler way, but haven’t seen anything that’s truly plug-and-play yet. Curious to see what you’re working on.
dieortin
It’s very obvious this account was just created to promote your product…
mkw5053 OP
I don't even have a product although I'd love people to work on something open source together. Also, I'm not nearly cool enough to earn a green username.
> This DevOps friction is exactly why I'm building an open-source "Firebase for LLMs."

i dont understand your earlier statement then

shwaj
I think they were replying to the person with the green user name :-)
androng
I think the way the friction could be reduced to almost zero was through OpenAI "custom GPTs" https://help.openai.com/en/articles/8554397-creating-a-gpt or "Alexa skills". how much easier can it get than the user using their own OpenAI account? Of course I'd rather have them on my own website but if were talking complete ease of use then I think that is a contender
mkw5053 OP
Fair point. I'm no expert in custom GPTs, I wonder what limitations there would be beyond the obvious branding and UI/UX control. Like, how far can someone customize a custom GPT (ha). I imagine any multi-step/agentic flows might be a challenge or impossible as it currently exists. It also seems like custom GPTs have been completely forgotten, but I very well could be wrong and OpenAI announced a big investment in them and new features tomorrow.
jeremyjh
Do you think Firebase and Superbase are working on this? Good luck but to me it sounds like a platform feature, not a standalone product.
mkw5053 OP
Probably some sort. In the meantime it doesn't currently exist and I want it for myself. I also feel like having something open source and that allows you to bring your own LLM provider might still be useful.
androng (dead)

This item has no comments currently.