​
Choose Your AI Provider

ClawBox is flexible about which AI model powers your assistant. You pick during setup and can change it later.

​
ClawBox AI (default)

Works immediately, no keys to manage. The simplest way to get started — and a great default for most people.

​
Bring your own provider

Prefer a specific model? ClawBox treats these as first-class options:

Anthropic Claude

Add your Anthropic API key to drive ClawBox with Claude models.

OpenAI GPT

Use your OpenAI API key for GPT models.

Google Gemini

Connect Gemini with a Google AI API key.

OpenRouter

One key, many models — route across providers.
To connect one, open the AI provider section of setup, choose the provider, and paste your API key. ClawBox stores it on the device.

​
Local models

For fully on-device inference, ClawBox supports local Ollama and llama.cpp models. This is an option for users who want it rather than the default path.
Local model performance depends on your hardware. ClawBox Workstation (DGX Spark, 128 GB unified memory) can run models up to ~200B parameters locally; ClawBox Connect (Jetson Orin Nano) is best paired with cloud providers or smaller local models. See Hardware.

​
Switching later

You can change provider any time from the device settings — no re-setup required.