I built a kind of paas for llms, the idea was to allow my family deploy webs cheap and easy, my family doesn't use It, but It end being very useful form mento deploy small apps. You can check It out on https://onvibe.run there is a list of forkable apps that I use.
I did some kind of meta thing, because bownI can create apps with llm (like Claude) and expose an mcp on theme (like the notes and todolist apps).
A project where you create websites by just using the chat interface of your llm. It's like a paas but oriented to llms. If your ui support mcp It should work.
My trick, I just use bootstrap, ask Claude for a custom Styles following a style, palete etc. Much better experience than buying and adapting and existing bootstrap theme
Great, I have a MacBook Pro M5 for work which i know IS really fast because the whole suite of specs run in les than two minutes, but except for that my "old" air m1 with 16g of ram feels super snappy.
I am just excited waiting future releases (in 5 or 10 years) able to run local llms for coding.
During the last year, in my spare time, I have been working on https://trypulso.com. The system has been working fine for the last year, and I have a real customer using it. I not even finished the landing page, but you can try it if you like.
Also, this Christmas I took a rest on Pulso, and I developed a small app to monitor the version & Support Lifecycle of large dependencies. https://stacktodate.club
I like Ruby on Rails + Postgres, GoodJob for background Jobs, sveltejs for complex widgets, bootstrap as CSS framework, vite for "compiling" the assets, deploy on Fly.io
Hi, I have been building https://babelfu.com, a translation service on top of Github; it fetches the translations from your GitHub repo and commits them back, so the source of truth of the translations is the repo itself. You can forget about sync tasks, collisions between branches, etc. In the end, if there are conflicts, you manage them on Git as the rest of your code.
It is available in a very early open-source version, which I will update at some moment if I see someone interested in it.
I would be very grateful if someone gave it a try to setup a project and provided some feedback.
I am doing nothing, but I was wondering if it would make sense to combine a small LLM and SQLITE to parse date time human expressions. For example, given a human input like "last day of this month", the LLM will generate the following query `SELECT date('now','start of month','+1 month','-1 day');`
It is probably super overengineering, considering that pretty good libraries are already doing that on different languages, but it would be funny. I did some tests with chatGPT, and it worked sometimes. It would probably work with some fine-tuning, but I don't have the experience or the time right now.
Yes, I read the "Rails" docs—the same that you linked—but I wanted to see how other projects use it. My surprise was that only a public project on Github uses it.