By popular demand, Loki is now Coyote!

I’ve just released a new version with the full rename.

Thanks to @minticecream@lemmy.world for the suggestion!

All the docs are updated except for the screenshots and gifs. I’ll update those tomorrow (since they don’t do any harm right now and don’t require another release to be updated).

For almost a year I’ve been using Loki as the name but it never really satisfied me. Not to mention it’s already the name of an extremely popular logging system by Grafana, which makes Loki hard to discover.

Got some great feedback and the rename was born! Thanks again everyone who gave suggestions and for all the positive feedback!

Unfortunately, yes. It’s one reason I’m trying to figure out a good mechanism to maybe do something like multiple ollama hosts. So like: you can specify what model to use specifically in an agent. But if an agent delegates to a sub-agent, it unloads that model and loads the new one. I’m trying to figure out if there’s a way to “alternate” between multiple hosts (say, ollama running locally and one running on your server), so that when a switch happens, it does it on the secondary host while also looking ahead to see what needs to be switched, if anything, on the primary host.

It supports multiple Ollama hosts right now as-is so what I’ve honestly been doing for the time being is specify which model on which host each agent uses so there’s only loading of one model at the beginning of a session. Then there’s no unloading/loading/etc. The other thing I’ve been trying is to see how small I can get the models to be without losing performance. While the tricks implemented in Loki help dramatically, I know there’s still a lot more I can do to improve it further.

I’m using a ton of different ones but the main ones I use daily are

• gemma4:26b
• deepseek-coder
• deepseek-r1:32b
• devstral:24b
• granite-code:34b
• openthinker:latest
• phi4:latest
• qwen3:30b
• mixtral:8x22b

I’m also going to use this opportunity to plug an amazing project to help figure out which models will work well on my hardware: https://github.com/AlexsJones/llmfit Is amazing!

They’re encrypted with a PSK encrypted with either AES128 or AES256. It’s built into the Meshtastic firmware so that’s not something I have to handle directly, thankfully!

I started thinking about using the LoRa protocol directly for this too! My biggest concern is overwhelming the mesh. But I also had no idea what protocol would work so thanks for mentioning PPP. I haven’t thought about that since I was a kid! That would be really cool though!

Maybe just for a POC someday?

Also: how are you liking MeshCore? Did you have to pay for a license to use it? How expensive is the mesh you’re building? That is something I’ve started thinking about too for this exact reason 😂

To answer your question, I built it for a few reasons:

• I wanted to learn Rust, so I used this project to do that
• I really love TUI’s and I pretty much live in my command line at work, and since I already automate everything I can to make my work life easier, I wanted to be able to do the same with my homelab
• I think it looks cool
• For fun. If no one else ever gets use out of it, that’s okay! I just really enjoyed building it and I’m excited to build out more of it.

But also: Why not? ☺️

So really, you would only use this if you like TUIs or want a command line tool for interacting with your Servarrs. If you have no use for it, that’s totally fine too!

The one actual use I’ve found people say they use it for is people who don’t want to expose the web interface to interact with their Servarrs and only interact via SSH. Then they like to use this instead.

No hate perceived on my end! To answer your question, I built it for a few reasons:

• I wanted to learn Rust, so I used this project to do that
• I really love TUI’s and I pretty much live in my command line at work, and since I already automate everything I can to make my work life easier, I wanted to be able to do the same with my homelab
• I think it looks cool
• For fun. If no one else ever gets use out of it, that’s okay! I just really enjoyed building it and I’m excited to build out more of it.

But also: Why not?

That’s amazing. Hello fellow Alex! 😂

You’re the first person to catch the reference! Sadly, no I’m not. But I was a prolific PSP modder as a kid so I knew his name and was very familiar with him. So, in my adult life, since he had such a big impact on me, my username is made after him! My real name is Alex so it just kind of worked.

Thank you so much! ☺️