Rune is a core piece of our technology that allows developers to create tinyML applications as containers. Think docker but much tinier. Rune is an orchestration tool for specifying how data should be processed, with an emphasis on the machine learning world, in a way which is portable and robust.
The main purpose of a Rune is to give developers in the fields of machine learning and data processing a way to declare how data should be transformed using a high-level, declarative language. Instead of needing to write code that manipulates data or needs to interface with complex third-party libraries for receiving inputs, you write a Runefile which declares each processing step and defers their implementation to the Rune runtime. This runtime then takes care of interfacing with the outside world and can leverage existing third-party libraries for data manipulation.
One of the applications that prompted Rune's creation was machine learning. In machine learning, there are often several pre and post-processing steps required to turn inputs into a form that is usable for a machine learning model and interpreting the results. These steps tend to be a distraction from the actual machine learning and are often cumbersome or boring to implement, so Rune comes with several built-in facilities specific to ML.
A big part of using WebAssembly is that the Rune is entirely sandboxed from the outside world. A faulty Rune can't accidentally bring down the rest of the application and can only access resources explicitly given to it by the Rune runtime. Both the Rune runtime and the Rune itself are written in Rust. This lets us leverage the language's strong type system and concepts like unsafe and the borrow checker to ensure correctness and protect against a lot of memory and concurrency bugs found in other systems languages.