KoboldCpp

by LostRuins (Concedo)

A single executable to run GGUF models with a web UI, great for writing and role-play.

12 k stars GitHub AGPL-3.0 Free when localLocalOpen sourceOpen weights

View on GitHub →

What it does

No install: one file to download and run
Built on llama.cpp, with CUDA, Vulkan or CPU acceleration
Also handles image generation and speech

Install it

Requirements: A model in GGUF format.

Download (Windows / macOS / Linux)

https://github.com/LostRuins/koboldcpp/releases/latest

Linux one-liner

curl -fLo koboldcpp-linux-x64 https://github.com/LostRuins/koboldcpp/releases/latest/download/koboldcpp-linux-x64 && chmod +x koboldcpp-linux-x64 && ./koboldcpp-linux-x64

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install KoboldCpp (https://github.com/LostRuins/koboldcpp) on my machine.
1. Check the requirements: A model in GGUF format. If anything is missing, tell me before installing anything.
2. Follow the official method:
- see https://github.com/LostRuins/koboldcpp/releases/latest
- Linux one-liner: curl -fLo koboldcpp-linux-x64 https://github.com/LostRuins/koboldcpp/releases/latest/download/koboldcpp-linux-x64 && chmod +x koboldcpp-linux-x64 && ./koboldcpp-linux-x64
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.