An optimized LMS algorithm

A framework for resonance-based decision-making in artificial agents, combining celestial influences, memory feedback, and symbolic emergence.

Dynamic Neural Network Refinement (DNNR) is an advanced framework that allows neural networks to adapt in real time. Unlike static systems, DNNR refines network parameters on-the-fly to optimize performance. Its modularity ensures easy customization for versatile applications.

End-to-end toolkit for smart hash maps, CLI, Mission Control (PyQt6) dashboard, Textual TUI, workload analytics, snapshots, and automated benchmarks.

Cognition made programmable.

Python hash map that migrates between two-level chaining and Robin Hood probing based on workload. Live metrics dashboard, reproducible workloads, CSV/JSON benchmarks, safe snapshots and repair.

🛠️ Build intelligent systems with this guide to agentic design patterns, simplifying the process for developers and enhancing capabilities in AI-driven projects.

Auto-generate specialized Claude Code subagents for your stack. Phase-adaptive code review. 10 frameworks, 13 templates. MIT licensed.

Connector OS: a modular human–AI architecture using adaptive control, feedback loops, and threshold-based stability. Includes the 8-layer stack, MVM modules, cross-domain validations, and practical examples. This is a practical framework, not an AGI claim.

Assignment in Sistem Adaptif(Adaptive System course)

A recursive, entropy-driven computational language for modeling emergent intelligence, consciousness, and complex adaptive systems. Features automatic bifractal tracing, field-aware memory, and entropy-gated execution for infodynamics research.

A simulation demonstrating that recursive intelligence vastly outperforms scalar IQ under collapse and drift. Based on the paper “Recursion vs. IQ: Toward a Multi-Scale Model of Intelligence v2.0