Profile-based launcher for local LLM servers - start, stop and switch models on llama.cpp, Ollama and LM Studio from one CLI/TUI. Zero resident overhead, optional MCP control plane, importable as a Go library.
Latest release v1.7.0 · 14 Aug 2026
1 file for Claude Code: llama-launcher CLAUDE.md — 33 tokens loaded in every session.
CLAUDE.md A 33 tok These files are airiclenz/llama-launcher's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.