CLI Tools
Command-line interface documentation for managing your Thox.ai device.
Installation
macOS / Linux
# Install via Homebrew
brew install thoxai/tap/thox
# Or via shell script
curl -fsSL https://get.thox.ai | sh
Windows
# Install via Scoop
scoop bucket add thoxai https://github.com/thoxai/scoop-bucket
scoop install thox
# Or via winget
winget install ThoxAI.CLI
npm (Cross-platform)
npm install -g @thoxai/cli
Verify Installation
thox --version
# Output: thox v1.2.0
Commands Reference
thox chat
Start an interactive chat session with your device.
# Interactive chat
thox chat
# Single message
thox chat "Explain this error: TypeError..."
# With specific model
thox chat --model thox-coder-large "Review this code"
thox models
Manage AI models on your device.
# List installed models
thox models list
# Download a new model
thox models pull thox-coder-large
# Remove a model
thox models rm thox-chat-small
# Show model details
thox models info thox-coder
thox status
Display device status and health information.
thox status
# Output:
Device: thox.local (192.168.1.100)
Status: Online
Temperature: 52°C
Memory: 8.2GB / 16GB
Storage: 45GB / 2TB
Active Model: thox-coder
thox config
Manage CLI and device configuration.
# Show current config
thox config show
# Set device address
thox config set host 192.168.1.100
# Set default model
thox config set model thox-coder-large
thox serve
Start a local proxy server for development.
# Start proxy on default port
thox serve
# Custom port
thox serve --port 3000
Configuration
Configuration File
The CLI stores configuration in ~/.thox/config.yaml
# ~/.thox/config.yaml
host: thox.local
port: 8080
default_model: thox-coder
timeout: 30s
streaming: true
# Output formatting
format: pretty # pretty, json, plain
color: auto # auto, always, never
# Aliases
aliases:
c: chat
m: models
s: statusEnvironment Variables
THOX_HOSTOverride device hostname/IPTHOX_PORTOverride device portTHOX_MODELOverride default modelTHOX_CONFIGCustom config file pathShell Completions
Enable tab completion for commands, flags, and model names in your shell.
Bash
# Add to ~/.bashrc
eval "$(thox completion bash)"
Zsh
# Add to ~/.zshrc
eval "$(thox completion zsh)"
Fish
thox completion fish | source
# Or save to completions directory
thox completion fish > ~/.config/fish/completions/thox.fish
PowerShell
# Add to $PROFILE
thox completion powershell | Out-String | Invoke-Expression
CONFIDENTIAL AND PROPRIETARY INFORMATION
This documentation is provided for informational and operational purposes only. The specifications and technical details herein are subject to change without notice. Thox.ai LLC reserves all rights in the technologies, methods, and implementations described.
Nothing in this documentation shall be construed as granting any license or right to use any patent, trademark, trade secret, or other intellectual property right of Thox.ai LLC, except as expressly provided in a written agreement.
Patent Protection
The MagStack™ magnetic stacking interface technology, including the magnetic alignment system, automatic cluster formation, NFC-based device discovery, and distributed inference me...
Reverse Engineering Prohibited
You may not reverse engineer, disassemble, decompile, decode, or otherwise attempt to derive the source code, algorithms, data structures, or underlying ideas of any Thox.ai hardwa...
Thox.ai™, Thox OS™, MagStack™, and the Thox.ai logo are trademarks or registered trademarks of Thox.ai LLC in the United States and other countries.
NVIDIA, Jetson, TensorRT, and related marks are trademarks of NVIDIA Corporation. Ollama is a trademark of Ollama, Inc. All other trademarks are the property of their respective owners.
© 2026 Thox.ai LLC. All Rights Reserved.