Seems cool!
I've been looking for something like this.
Especially if it can be used as a collaborative knowledge management tool for team knowledge bases.
I started working toward self hosting LLM for my small company using ollama and opencode as agent
But I realized a good model like GLM 5 requures 250GB of RAM and 24GB vram with a 4080??
I dont know, this is what the LLM told me itself.
I ended up using qwen-code2.7-7b-16k.
Currently the best thing I have is my laptop, 16GB ram, i7 9750H gtx1650
How do you guys selfhost? What models do you use that are actually good?
Nano is for chemists maybe. Editing couple of lines and saving.
But vim is one of the most powerful text editors ever created. It's so powerful and good that it gets ridiculous.
Also, from an ergonomic standpoint, your body will thank you for using vim/neovim
I think edn is almost the only more advanced and ergonomic option to json. Edn is like the evolved json, but its interesting that its roots are way older than JSON.
The fact that you can very efficiently define whole applications and software just with edn (and the lisp syntax in general) is what makes really amazing.
I think this blog post sheds more light on how we only need lisp for defining data and applications.
I honestly think it would be much cooler if linux used semantic versioning instead of random versioning, but Linus bumping majors just because he feels like it is also funny and cool.
If you're a GUI guy, catfish is good.
If you're a term guy, fzf, rg, fd are very fast and powerful. I search for files in / (meaning EVERYTHING) and tge results are there in less than 10 seconds.
This blog post has some example usages, read the entries for fzf, rg and fd.
Well...
I am a very hairy nerdy guy. What does the collaboration workflow look like? The end result should be simple because my teammates aren't hairy nerdy guys :))
Thanks. I will look into it.