Hi all! I created 'Ariel', an MCP-exposed python REPL for LLMs to directly control robots.

The basic idea is: the most impressive ability of contemporary AI is not predicting the next torque, but writing code. So this approach leans into that all the way. Unlike VLAs or diffusion, it requires no additional training data and generalizes instantly to all robots. At least for this trivial robot, it works well!