llama-buddy 0.1.4

CLI wrapper for llama.cpp providing an ollama-like experience

llama-buddy

A friendly CLI wrapper for llama.cpp

Manage, download, and serve local LLMs with a single command. Think of it as an ollama-like experience built on top of llama-server.

---

Features

• Background server — start/stop/restart llama-server as a daemon
• Multi-model routing — preset-based configuration with automatic model load/unload
• Interactive downloads — search HuggingFace, pick a quant, download with progress and resume
• Rich terminal UI — tables, panels, interactive selectors, and live search
• GGUF inspector — view model metadata, architecture, and sampling parameters
• Per-model settings — context size, GPU layers, flash attention, and more
• Idle model unloading — background watchdog automatically unloads models after configurable idle timeout
• VRAM tracking — automatically parses server logs to show memory usage per model
• Auto-sync — preset file stays in sync with the llama.cpp cache automatically

Screenshots

Model listing — llb models

Interactive download — llb download

Model info — llb info

Installation

pipx install llama-buddy

Or with uv:

uv tool install llama-buddy

This installs the llb command into an isolated environment and adds it to your PATH.

Prerequisites

• Python 3.10+
• llama.cpp installed and llama-server on your PATH

Quick start

# Download a model (interactive search)
llb download

# Or specify directly
llb download mistralai/Ministral-3-3B-Instruct-2512-GGUF:Q4_K_M

# Start the server
llb start

# List all models
llb models

# Chat with a model (uses llama-cli)
llb chat

# Inspect model metadata
llb info

# Configure settings (interactive TUI)
llb settings

# Open the web UI in your browser
llb open

# Stop the server
llb stop

Commands

Command	Description
llb start	Start llama-server in the background. Extra args are forwarded.
llb stop	Stop the running server.
llb restart	Restart the server.
llb status	Show whether the server is running.
llb models	List all models with status, size, VRAM usage, and grouping. Supports --sort size.
llb download [model]	Download a model. Interactive HF search when no model given.
llb remove [model]	Remove a model with confirmation dialog. --keep-files to preserve GGUFs.
llb info [model]	Show GGUF metadata. Interactive selector when no model given.
llb settings	Interactive editor for global and per-model settings.
llb chat [model]	Interactive chat via llama-cli. Model selector when no model given.
llb open	Open the llama-server web UI in your browser.
llb logs	Tail the server log file.

Configuration

Config files live in ~/.config/llama/:

File	Purpose
models.ini	Model preset file — sections are HF repo IDs, auto-synced with cache
settings.json	Global server settings (port, context size, GPU layers, etc.)
vram.json	Cached per-model VRAM usage (parsed from server logs)
server.pid	PID of the running server
server.log	Server stdout/stderr

Per-model settings

Run llb settings and select Model Settings to configure per-model overrides:

• Context size, GPU layers, flash attention
• Custom aliases
• Any llama-server parameter

Development

# Clone and install
git clone https://github.com/thilomichael/llama-buddy.git
cd llama-buddy
uv sync

# Run
uv run llb <command>

# Test
uv run pytest

# Lint
uv run ruff check src/ tests/

License

MIT