Hey, I automate tmux all the time with send keys and capture.. how is your project improves vs tmux or zellij?

rmux is much faster than tmux or zellj, I did some internal benchmark and it's promising. rmux is a multiplexer engine, meaning that you can rewrite entirely zellij using rmux.. I created a mini zellij in a few hundred lines of rust. You can check the demoes on the repo

But wait, I’m a user of tmux or zellij which for me was basically another tmux and I went back to tmux eventually. I’m not looking to develop another tmux or something. Is this project more of a library to create tmux like apps?

As of today you can replace tmux by rmux. Its behavior should be 1-1 iso; tmux is more stable though, it has been battle tested with a dozen of years of edge cases refinement. rmux is a faster and more elegant clone of tmux + windows support + programmable sdk

I don't get it as well, everything mentioned in the readme is already trivially possible with tmux or zellij

windows support + async + public sdk. You can rewrite zellij with rmux, but not the opposite. rmux is a multiplexer engine

I mean, the obvious immediate answer is “windows”, which tmux flat out doesn't support (except via WSL and a shared mount).

Hey, this is most probably related to the chat template or the reasoning parser or the tool call parser or also things like kv cache quantization and possibly other params that affect results like the regular top k top p and all of that, the backend often sets its own defaults or the lack of them. It’s best to have all these under control if possible. I wonder regarding this project have you been testing it on real world projects? I’m working on an agentic loop as well also using a local model.

Yes I've now used it "in the wild" for a handful of use-cases. I still run into the backend thing even when declaring params though, which is odd to me. But there might be params not typically passed in with the model that backends are setting. Again, really not my area of expertise.

As for consumers, I've done a home assistant, an agentic coding harness, and an autonomous engineering project (still in flight).

Nice. Very clean api.

Thanks. Main goal. Unions is where I decided to pause - no simple and ergonomic way to do it at the moment.

For anyone that ever reads this, the issue was associated with the zoom level, up to a certain zoom level it behaves ok and wraps the text.

Worked fine for many years for me. Not great, but usable.

I mean in portrait. In landscape it’s fine.

May we still use the agent sdk for our own private use with the max account? I’m a bit confused.

How this compares with other libs and frameworks ?

It's more performant than other similar libraries such as the Owner and cfg4j which no longer seems to be actively developed at this point and others such as Spring's Environment and MicroProfile config implementations

See benchmarks here: https://github.com/joel-jeremy/java-config-library-benchmark...

Aside from the performance, the other advantage of using this config library is how it makes testing easier and how easy it is to integrate with your dependency injection frameworks of choice.

Nice. Vanilla js with a pretty clean code. From a quick look there is some components architecture and they are decoupled via an events bus. I used to implement evented architectures in winform apps in the past. On the one hand it may seem insane but in practice it was a really good choice.

Hmm so how are the alternatives? Just in case I will get banned for nothing as well. I’m riding cc with opus all day long these days.

I'm using Google's antigravity & it works fine for my use cases.