sheo

I have a skill named read-opencode-db that's literally a 5 line md file as a simple documentation for a python script that allows agent to read other sessions

It's meant for me to reference session ID's directly to look at another agent review results for example

But I don't think that my workflow is well suited for allowing agents to freely grep the database for facts or decisions, I prefer Matt Pocock's domain modelling skill that bakes decisions into versioned and commitable markdown files

I saw like 20 tools of this kind and there is a new one coming every month. Cursor had something like this at some point. They've removed it

Referencing other sessions is a cool idea tho

As said in the article, all of the providers run different runtimes with proprietary, sometimes untested and weird optimisations

There are multiple types of quantisation: weights and KV Cache. Quantizing kv cache can drastically hurt performance

Because there is no single "default instance that is always a good choice and wouldn't go down randomly because of lack of funding". That's both a strong and a weak side of fedi

I think Forgejo is great. But we need to remember the fact that many enterprises pick GitHub or GitLab because they provide paid support and SLA. Also Forgejo Actions are still in beta, while GitLab and GitHub are pretty established solutions for CI/CD

Sourcehut is basically a really barebones web interface for git server, so I don't think it's really comparable to GitHub

For hosting your own projects that's sometimes not a viable solution either. Limiting your open source project to platform other than GitHub hurts it's discoverability, because usually GitHub is what most devs and non devs associate with open source. I heard a lot of "It's not open source if it's not on GitHub". You can mirror your project to GH of course

"Just migrate to X because it's faster" doesn't work that well in the real world

I think that the example in the article is not a good usecase for this technology. It would be better, cheaper and less error prone to have prebuilt forms that LLM can call like tools, at least for things like changing shipping address

Shipping forms usually need verification of addresses, sometimes they even include a map

Especially if on the other end data that would be inputted in this form, would be stored in the traditional DB

Much better usecase would be use it in something, that is dynamic by nature. For example, advanced prompt generator for image generation models (sliders for size of objects in a scene; dropdown menus with variants of backgrounds or style, instead of usual lists)