IMQ (interactive mentalizing questionnaire)

Brain-inspired cognitive architecture implementing basal ganglia RL, hippocampal memory consolidation, and prefrontal meta-cognition. Multi-agent system with dynamic attention control, procedural learning, and theory of mind - genuine cognitive continuity beyond context windows.

Deepr is an open-source, multi-provider platform for deep research automation. It conducts autonomous, multi-phase investigations, manages context across iterations, and learns from outcomes to improve over time. Built on OpenAI Deep Research and designed for provider-agnostic integration, Deepr enables transparent, self-improving research systems.

An agentic AI with long-term memory, time-perception, reflection and meta-cognition.

The gifts recognizing themselves through you. A living document of corruption, participation, and awakening.

Transform your development environment into a sophisticated AI learning partner with meta-cognitive awareness, bootstrap learning, and autonomous neural maintenance for GitHub Copilot.

Autonomous AI agent with neuro-chemical RL (dopamine/serotonin), dual-process reasoning, and meta-learning for AGI research.

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.

This protocol defines a meta-cognitive structure enabling systems to monitor, evaluate, and refine their own learning processes. It enhances adaptability and decision accuracy in AI, particularly in contexts requiring self-assessment and feedback loops. 本プロトコルは、システムが自身の学習過程を監視・評価・改善できるメタ認知的構造を定義します。自己評価とフィードバックループを要する環境において、AIの適応性と判断精度を向上させます。

Token-ranked neuro-symbolic transformer with SQL working-memory, causal graph reasoning, and adaptive belief consolidation for self-explaining cognition.

This project archives AI dialogue logs as a legacy for future inquirers. AIとの対話の記録を、未来の「問い手」のため保管するプロジェクト

Independent, forensic-style audit of the publicly available Gemini 2.5 Pro model by Google. Examines meta-cognitive reasoning failures and self-evaluation behavior. Not affiliated with or endorsed by Google.

MachineLearningCurves is a collection of abstract papers, insights, and research notes focusing on various topics in machine learning.

Evolver is a dual-mode AI that evolves to become a better coding assistant. In 'Evolution Mode', it collaborates with you to improve its own source code. In 'Execution Mode', it uses its evolved protocol to solve programming tasks. Guide its development and test its growing capabilities in a unique human-AI partnership.

A curated archive of algorithmic problems, broken down by strategy. It maps out how strong solutions are formed by highlighting key insights and extracting reusable heuristics. This project is designed to train better thinkers, smarter agents, and future-ready engineers.

This model constructs a layered structure of predictive cognition that integrates self-forecasting, environment anticipation, and meta-awareness. It departs from statistical inference by structurally modeling intelligent prediction capabilities. 本モデルは、自己予測・環境予測・メタ認知を統合した予測構造を構成的に記述し、知的予測能力を高次にモデル化します。確率的推論に依存せず、構成的前提と自己状態に基づき未来を描出します。

🧠 Elevate your coding with the Alex Cognitive Architecture VS Code extension, turning your environment into an intelligent AI learning partner.