Consensus-free distributed resource-sharing mesh for edge fleets, pairing discrete exterior calculus with hierarchical active inference.
AXON v1.5.1 — first crates.io publication of the AXON language full-stack runtime. Lexer/parser/type-checker/IR generator (re-exported from axon-frontend) plus the native Rust runtime: typed channels (TypedEventBus with QoS×5, π-calculus mobility, capability extrusion via shield D8 — Fase 13.f.2), Free Monad CPS handlers (Fase 2), lease kernel + reconcile loop (Fase 3+5), Epistemic Security Kernel (ESK Fase 6), Trust Types + ReplayLog (Fase 11.a+11.c), Stateful PEM over WebSocket (Fase 11.d), Ontological Tool Synthesis (Fase 11.e), Mobile Typed Channels (Fase 13). Crate publishes as `axon-lang` to mirror the Python PyPI package; library import remains `use axon::*` so existing call sites keep working unchanged.
Persistent synthetic identity and topological stabilization for MimirsWell
Free Energy Principle active inference — generative models, precision-weighted prediction errors, and motor control
Consensus-free distributed resource-sharing mesh for edge fleets, pairing discrete exterior calculus with hierarchical active inference.
Consensus-free distributed resource-sharing mesh for edge fleets, pairing discrete exterior calculus with hierarchical active inference.
Consensus-free distributed resource-sharing mesh for edge fleets, pairing discrete exterior calculus with hierarchical active inference.
Consensus-free distributed resource-sharing mesh for edge fleets, pairing discrete exterior calculus with hierarchical active inference.
Consensus-free distributed resource-sharing mesh for edge fleets, pairing discrete exterior calculus with hierarchical active inference.
Consciousness substrate for ExoGenesis Omega - IIT, Free Energy Principle, and Global Workspace
Per-tool reliability beliefs (Beta distribution) + task-level uncertainty for LLM agents. Bayesian updates each turn drive Expected Free Energy scoring and epistemic escalation. Part of the Synthetic Consciousness Framework.
Bit-packed VSA (MAP-B) memory engine with power-law decay and surprise-driven episodic segmentation.