The open-source AxonOS project is developing a software infrastructure for systems with a brain-machine interface (BMI), designed to build a deterministic execution layer between neural hardware and AI. The AxonOS kernel is developed in Rust in "no_std" mode, with an emphasis on predictable real-time execution, a formalized system call ABI, a lock-free IPC capability model, and runtime control. The source code is open source under the MIT or Apache 2.0 licenses.
The project includes a kernel/runtime, BCI integration, architectural specifications, a consent/permissions model, and real-time analysis tools. AxonOS is currently being developed for ARM Cortex-M processors and is undergoing hardware verification and independent real-time performance testing. The AxonOS architecture views brain-machine interfaces as a multi-layered system: brain-machine device → HAL → deterministic runtime → IPC → permissions/consent access model → application and AI layer.
The project's main idea is to create a controlled application execution layer operating between a neural network device and an AI, in which requirements for determinism, isolation, neural data access, and response time are part of the system architecture, rather than a function of the application. A separate focus of the project is analyzing the worst-case response time (WCRT) for fixed-priority tasks. For this purpose, an independent tool, "dy-wcet," is being developed—a "no_std" Rust crate package implemented without the use of floating-point operations.
Source: opennet.ru
