muthr

muthr is a zero-trust orchestrator that automates llama.cpp and Lima to safely run local AI agents. Running coding agents on your machine exposes your system to unpredictable tool calls. muthr prevents this by managing the lifecycle of both tools: it controls inference via a host-based llama-server and spawns isolated Lima VMs for agent execution. Agents get full read-write access to your project workspace, but zero access to the host OS or SSH keys.

Usage

muthr serve              # Start llama-server as a background daemon
muthr serve --foreground # Run in foreground
muthr status             # Check engine status and active profile
muthr stop               # Stop the engine

muthr up    # Provision a Debian 13 VM for the current project
muthr ls    # List all active sandboxes
muthr down  # Stop the current sandbox

muthr services start     # Launch MCP services VM
muthr services status
muthr services stop

Architecture

1. llama-server on macOS, accelerated via Metal
2. limactl VMs provisioned per-project
3. OpenCode inside guest VMs, connecting over host.lima.internal

Prerequisites

macOS (Apple Silicon, ≥48GB RAM for 35B models), Lima, llama.cpp

Configuration

Config in ~/.config/muthr/:

• llama/presets/*.ini — context sizes, threading, model paths
• lima/templates/*.yaml — VM architecture, memory, container configs
• lima/provision/*.sh — boot scripts for OpenCode CLI and dependencies

Runtime state (PID files, logs, generated JSON) in ~/.cache/muthr/.

Installation

muthr is part of tappunk/dotfiles. Install it by following the dotfiles instructions.