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 / 256GB
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