Introducing LlamaStash: a zero-overhead, terminal-native llama.cpp launcher

1. llamastash

   1 3 4 - Rust

   A fast terminal native app (TUI) and CLI with init wizard for launching local LLMs via llama.cpp with zero overhead

   

   That script grew up. Today I'm releasing LlamaStash, the first public release of a fast, cross-platform, terminal-native launcher for llama.cpp with zero overhead.

2. SaaSHub

   www.saashub.com featured

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

3. llama.cpp

   2 1,035 115,929 10.0 C++

   LLM inference in C/C++

   

   That script grew up. Today I'm releasing LlamaStash, the first public release of a fast, cross-platform, terminal-native launcher for llama.cpp with zero overhead.

4. kdash

   3 15 2,473 9.2 Rust

   A simple and fast dashboard for Kubernetes

   

   I love terminal UIs (see KDash, JWT-UI, and battleship-rs). I wrote KDash, a Kubernetes dashboard TUI in Rust. That was 2020. The Rust TUI ecosystem at the time was tui-rs and a lot of patience. Threading was DIY. Layouts were arithmetic. State management was you-figure-it-out.

5. jwt-ui

   4 1 293 - Rust

   A command line UI for decoding/encoding JSON Web Tokens

   

   I love terminal UIs (see KDash, JWT-UI, and battleship-rs). I wrote KDash, a Kubernetes dashboard TUI in Rust. That was 2020. The Rust TUI ecosystem at the time was tui-rs and a lot of patience. Threading was DIY. Layouts were arithmetic. State management was you-figure-it-out.

6. tokio

   5 235 32,273 9.6 Rust

   A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...

   

   Building LlamaStash brought me back to a lot of that, but the ground has shifted. ratatui (the maintained fork of tui-rs) is a real, polished framework now. tokio makes async daemons boring in a good way. hyper gives you a respectable HTTP server in a few hundred lines. crossterm handles the cross-platform terminal mess. sysinfo covers host metrics. The pieces are all there and you have LLMs to help you speed up everything to 10x.

7. battleship-rs

   6 2 96 2.1 Rust

   A terminal battleship game in Rust

   

   I love terminal UIs (see KDash, JWT-UI, and battleship-rs). I wrote KDash, a Kubernetes dashboard TUI in Rust. That was 2020. The Rust TUI ecosystem at the time was tui-rs and a lot of patience. Threading was DIY. Layouts were arithmetic. State management was you-figure-it-out.

8. ratatui

   7 28 21,005 9.6 Rust

   A Rust crate for cooking up terminal user interfaces (TUIs) 👨‍🍳🐀 https://ratatui.rs

   

   Building LlamaStash brought me back to a lot of that, but the ground has shifted. ratatui (the maintained fork of tui-rs) is a real, polished framework now. tokio makes async daemons boring in a good way. hyper gives you a respectable HTTP server in a few hundred lines. crossterm handles the cross-platform terminal mess. sysinfo covers host metrics. The pieces are all there and you have LLMs to help you speed up everything to 10x.

9. crossterm

   8 35 4,095 5.3 Rust

   Cross platform terminal library rust

   

   Building LlamaStash brought me back to a lot of that, but the ground has shifted. ratatui (the maintained fork of tui-rs) is a real, polished framework now. tokio makes async daemons boring in a good way. hyper gives you a respectable HTTP server in a few hundred lines. crossterm handles the cross-platform terminal mess. sysinfo covers host metrics. The pieces are all there and you have LLMs to help you speed up everything to 10x.

10. sysinfo

    9 14 2,699 8.9 Rust

    Cross-platform library to fetch system information

    

    Building LlamaStash brought me back to a lot of that, but the ground has shifted. ratatui (the maintained fork of tui-rs) is a real, polished framework now. tokio makes async daemons boring in a good way. hyper gives you a respectable HTTP server in a few hundred lines. crossterm handles the cross-platform terminal mess. sysinfo covers host metrics. The pieces are all there and you have LLMs to help you speed up everything to 10x.

11. ollama

    10 754 173,924 9.9 Go

    Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

    

    On the other side, Ollama and LM Studio wrap llama.cpp in friendlier shells. Ollama is opinionated about model storage, format, and config. LM Studio is GUI-first and not terminal native. Both pay a real performance cost compared to raw llama-server, and both hide the underlying primitives that I actually like working with.

12. scoop-llamastash

    11 1 0 -

    Scoop bucket for llamastash — fast, keyboard-driven TUI for running local models via llama.cpp

    

    # macOS + Linux, one-shot installer curl -fsSL https://llamastash.dev/install.sh | sh # Homebrew (macOS + Linuxbrew) brew install llamastash/llamastash/llamastash # Arch Linux (AUR) yay -S llamastash # source build from the tagged GitHub release yay -S llamastash-bin # prebuilt x86_64 / aarch64 tarball yay -S llamastash-git # main-branch checkout, rebuilds on every -Syu # Windows 11 (PowerShell, no admin elevation) irm https://llamastash.dev/install.ps1 | iex # Windows via Scoop bucket scoop bucket add llamastash https://github.com/llamastash/scoop-llamastash && scoop install llamastash # crates.io (any platform with a Rust toolchain) cargo install llamastash

13. servers

    12 404 87,066 9.8 TypeScript

    Model Context Protocol Servers

    

    MCP server surface. The CLI is already agent-friendly, so I'm double minded about whether a Model Context Protocol server would make integration smoother. I'm personally not a fan of MCP and prefer skills and CLIs.

14. hyper

    13 111 16,130 8.0 Rust

    An HTTP library for Rust (by hyperium)

    

    Building LlamaStash brought me back to a lot of that, but the ground has shifted. ratatui (the maintained fork of tui-rs) is a real, polished framework now. tokio makes async daemons boring in a good way. hyper gives you a respectable HTTP server in a few hundred lines. crossterm handles the cross-platform terminal mess. sysinfo covers host metrics. The pieces are all there and you have LLMs to help you speed up everything to 10x.

15. catppuccin

    14 68 19,288 8.6 TypeScript

    😸 Soothing pastel theme for the high-spirited!

    

    Five themes plus custom. Catppuccin Macchiato is the default because of course it is.

16. agentskills

    15 64 20,399 8.9 Python

    Specification and documentation for Agent Skills

    

    There is also an Agent Skills bundle in the repo that teaches your coding agent to use the CLI properly. Drop it into your OpenCode, OpenClaw, or Claude Code skills directory and the agent learns to prefer --json, branch on exit codes, and read status --json before configuring an OpenAI-compatible client.

Suggest a related project