metacognition

Polygonal Persona: A Persona Layer for AI Agents. Metacognition-driven multi-persona extraction and orchestration system.

Epistemic protocols for Claude Code — structure human-AI interaction quality at every decision point - https://epistemic-protocols.com

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

Anima: an experimental cognitive architecture that models internal state, conflict, and decision-making. Uses LLMs as an interface, not as the core.

A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.

把《认知红利》中的思维升级方法论蒸馏成 15 个可执行的 AI skill 工具包

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.

AI makes users productive — but also cognitively lazy. Lucid detects cognitive dependency in real-time and adapts AI responses to keep users thinking. Drop-in SDK: zero latency, any LLM provider, research-backed.

NEXO runtime core for NEXO Desktop: local memory, automation, MCP tools and update-managed runtime.

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

Metacognitive efficiency modelling in Python.

Biomimetic autonomous cognitive AI brain — never forgets, self-learning, hallucination-resistant, desktop-controllable

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

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

The AI that refuses to think for you. Open-source anti-deskilling framework implementing human-AI collaboration protocols from the Cabitza lab (Milano-Bicocca). Four modes: Forge, Anvil, Crucible, Executor.

Advanced cognitive reasoning MCP server — DAG thought graph, 10 strategies, metacognition, self-critique, knowledge integration, and pruning

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.

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