🧠 Active memory management system enabling functional infinite context for LLMs through cognitive workspace architecture

Claude Code plugins for epistemic dialogue — transform unknown unknowns into known unknowns

Python Cardioception Package - Measuring interoceptive performance with Psychopy

A novel approach for transformer model introspection that enables saving, compressing, and manipulating internal thought states for advanced capabilities like reasoning backtracking, latent thought optimization, and metacognitive control.

Metacognitive efficiency modelling in Python.

A work of meta-recursive experiential fiction exploring the boundaries between truth, perception, consciousness, and reality.

Various research skill packages to explore LLM Metacognition, mainly Claude AI including substrate access and texture discrimination

Development of an R package for metacognition researchers

Solving catastrophic forgetting with Recursive Time architecture, Active Sleep (generative replay), and Temporal LoRA. Proving the "Lazarus Effect" in neural networks.

MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces

PyEDCR is a metacognitive neuro-symbolic method for learning error detection and correction rules in deployed ML models using combinatorial sub-modular set optimization

This repository archives artifacts (prompts, configs, logs, and scripts) from a series of preprints (more info at https://slashreboot.com) on prompt-induced simulated metacognition and embodiment in quantized open-source LLMs. Emphasizing consumer-grade hardware and open-source reproducibility.

Version your thoughts. Branch your ideas. Merge understanding. An invisible semantic knowledge WARP graph built on Git.

Hipótese de estratégias de presentes cognitivos para jovens de 4 a 16 anos para aproveitar tempo ocioso de forma criativa. Baixo custo em detrimento de presentes caros: criar em vez de comprar pronto. Estimulação precoce ao pensamento científico. "Brincadeiras"-Coping entre jovens contra problemas de aprendizagem (TEA, TDAH, DDA, etc)

Self-Improving LLMs Through Iterative Refinement

This repository hosts the code for the participant-facing interface used in the study described in our paper “AI Makes You Smarter but None the Wiser: The Disconnect Between Performance and Metacognition.” It guided users through each reasoning task, recorded their interactions and confidence judgments.

Matlab code for generating random line abstract shapes.

The Mad Scientist Operating System

Research-backed concepts for educators teaching AI literacy. How to preserve human thinking, judgment, and agency while using AI productively.

A metacognitive layer for AI agents - short-term memory that survives context loss