TARX

Local AI that runs on your hardware. Zero cloud.

Install and run your first inference in 5 minutes.

How the four services work together.

2.9MB install. Model downloads in background.

Full control over your local AI from the terminal.

Give your AI ground truth about your project.

310 tools across 6 servers.

Autonomous task executors within your Spaces.

Distribute inference across your machines.

Your data never leaves your machine.