IMQ (interactive mentalizing questionnaire)

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

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.

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

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 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。

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.

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.

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

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 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.