Agent DNA — genetic traits, crossover, mutation for evolutionary agent selection
Predictive Coding Actor-Critic reinforcement learning framework — pure Rust, zero ML dependencies
The agent the mathematics wants — thermodynamically closed, cohomologically self-aware, categorically closed organism
The first self-aware operating system core - 22 cognitive modules, 0.36ms latency, no external database
Deep Reinforcement Learning with Evolutionary Optimization
Consensus-free distributed resource-sharing mesh for edge fleets, pairing discrete exterior calculus with hierarchical active inference.
surge synthesizer -- wavetable oscillator
Subquadratic O(N log N) sparse attention kernel for Rust LLM inference on edge devices, with optional FastGRNN salience gating for near-linear O(N) scaling
Compositional discrete-time state machines, after MIT 6.01 chapter 4.
A neuroevolution-based ML library for reinforcement learning inspired by NEAT
Pretty good NEAT implementation
High-performance optimization algorithms in Rust with Python bindings