metacognition

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

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

🧠 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.

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

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

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 local CLI for logging predictions before the outcome and checking whether your "80% sure" comes true 80% of the time.

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

Metacognitive efficiency modelling in Python.

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

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

Development of an R package for metacognition researchers

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.

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

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

A persistent Minecraft inhabitant that remembers, feels functionally, forms habits, pursues goals, and learns how to live