llamastash

Install command: 
brew install llamastash

Terminal-native local LLM orchestrator and proxy

https://github.com/llamastash/llamastash

License: MIT

Development: Pull requests

Formula JSON API: /api/formula/llamastash.json

Formula code: llamastash.rb on GitHub

Bottle (binary package) installation support provided for:

macOS on
Apple Silicon		 golden gate ✅
tahoe ✅
sequoia ✅
Linux ARM64 ✅
x86_64 ✅

Current versions:

stable ✅ 0.11.0
head ⚡️ HEAD

Depends on:

llama.cpp 0.9.0 LLM inference in C/C++

Depends on when building from source:

pkgconf 3.0.10 Package compiler and linker metadata toolkit
rust 1.99.1 Safe, concurrent, practical language

Binaries: llamastash

Service:

Start now and at login: brew services start llamastash
Run directly: $HOMEBREW_PREFIX/opt/llamastash/bin/llamastash --llama-server $HOMEBREW_PREFIX/opt/llama.cpp/bin/llama-server daemon start --foreground

Analytics:

30 days90 days365 days
Installs000
Installs on Request000
Build Errors0