cognitive-memory

Name: cognitive-memory
Availability: InStock
Author: rockdong

Route user-triggered memory content to core, episodic, semantic, procedural, and vault stores.

Updated Dec 31, 2025

Search Tags:#multi-agent #triggers #knowledge-graph #audit-trail #memory-management #cognitive-memory #decay-scores

Ready to run

npx skills add https://github.com/rockdong/stock_for_cpp --skill cognitive-memory

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cognitive-memory
Source: https://github.com/rockdong/stock_for_cpp/tree/main/skills/cognitive-memory
Command: npx skills add https://github.com/rockdong/stock_for_cpp --skill cognitive-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Intelligent multi-store memory system provides structured memory stores (core, episodic, semantic, procedural) with decay, reflection, and audit trails, enabling robust, auditable memory management for agent systems.

Core Features & Use Cases

Multi-store memory architecture (core/episodic/semantic/procedural) with decay, versioned history, and audit trails
Sleep-time reflection for philosophical evolution and guided memory consolidation
Shared read / gated write access for multi-agent collaboration
Knowledge graph integration and dynamic decay-based relevance scoring
Trigger handling (remember/forget/reflect) that updates MEMORY.md, decay-scores.json, and graph index

Quick Start

Initialize the memory workspace and load the cognitive-memory templates to bootstrap the system.

Frequently Asked Questions about cognitive-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I implement long-term memory management for a multi-agent system?▼

Long-term memory management for multi-agent systems routes triggered content into structured stores like core, episodic, semantic, and procedural. It updates graph indices and decay scores to maintain relevance across interactions.

How does decay-based relevance scoring work for agent memory?▼

Decay-based relevance scoring tracks memory usage over time to dynamically adjust importance. It updates a decay-scores.json file during remember or reflect actions, ensuring outdated information is deprioritized.

Do I need Python 3 to set up the cognitive-memory workspace?▼

Yes, Python 3 is required to initialize the memory workspace and load the cognitive-memory templates. This setup bootstraps the multi-store architecture and prepares the system for agent collaboration.

What is the best way to secure shared memory access for multiple agents?▼

Securing shared memory access uses gated write controls and mandatory backups to prevent data loss or leakage. It allows multiple agents to read shared stores while restricting write permissions to authorized triggers.

How do remember and forget triggers update the knowledge graph?▼

Remember and forget triggers classify memory content and update the knowledge graph index along with MEMORY.md. This ensures the graph accurately reflects current relationships and removes forgotten associations.

What happens during sleep-time reflection for memory consolidation?▼

Sleep-time reflection consolidates memories by evaluating decay scores and guiding philosophical evolution of stored content. It updates audit trails to maintain an auditable workflow of structural changes.