skills.rest
tiankong0101-byte
tiankong0101-byteCOMMUNITY
Explore all skills by this author →
GitHub

cognitive-memory

Organize persistent AI memory into episodic, semantic, procedural, vault, and core stores.

Updated May 17, 2026
Search Tags:#knowledge graph#agent workflow#retrieval#memory#reflection#audit trail#long-term context
One-click install
npx skills add https://github.com/tiankong0101-byte/skills-registry --skill cognitive-memory-tiankong0101-byte
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cognitive-memory
Source: https://github.com/tiankong0101-byte/skills-registry/tree/main/skills/cognitive-memory
Command: npx skills add https://github.com/tiankong0101-byte/skills-registry --skill cognitive-memory-tiankong0101-byte

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the problem of fragile, short-lived AI context by providing a durable memory system for agents. It helps the model remember important decisions, user preferences, project state, and long-term knowledge across sessions instead of relying on chat history alone.

Core Features & Use Cases

  • Multi-store memory architecture: Organizes information into episodic, semantic, procedural, vault, and core memory layers so the right information is stored in the right place.
  • Knowledge graph and retrieval: Supports entity tracking, relationship mapping, hybrid search, and graph traversal for fast recall of facts and connections.
  • Consolidation and maintenance: Includes reflection, decay, hygiene, audit logging, and upgrade workflows to keep memory relevant and manageable over time.
  • Use case: An agent can remember a user’s preferences, revisit past decisions, and reconstruct project context even after compaction or restarts.

Quick Start

Ask the agent to initialize the cognitive memory workspace and start tracking important facts, preferences, and decisions.

Frequently Asked Questions about cognitive-memory

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

FAQPage Schema
How do I maintain long-term context and memory for an agent workflow across sessions?▼

To maintain long-term context across sessions, you need a durable memory system that organizes persistent AI memory into multiple stores for long-term recall, reflection, and maintenance, preserving user preferences, project decisions, and semantic relationships.

What is the best way to structure semantic relationships and entity tracking for AI recall?▼

The best way to structure semantic relationships is by using a knowledge graph that supports entity tracking, relationship mapping, hybrid search, and graph traversal for fast recall of facts and connections.

How do I prevent stored agent memory from becoming irrelevant or bloated over time?▼

To prevent memory from becoming bloated, apply memory consolidation techniques like reflection, decay, hygiene, audit logging, and upgrade workflows to keep stored knowledge relevant and manageable over time.

Does cognitive-memory work with YAML for managing agent memory state and audit history?▼

Yes, cognitive-memory lists YAML as a dependency and uses initialization scripts, ontology utilities, and markdown reference files to manage memory state, retrieval, decay, and audit history.

How are episodic, procedural, and vault memories organized within a long-term agent context?▼

Long-term agent context is organized into a multi-store memory architecture that separates information into episodic, semantic, procedural, vault, and core memory layers so the right information is stored in the right place.

Related Skills

Explore More Software Engineering Skills→
papachongpapachong
2

memory-manager

Initialize three-tier agent memory and detect compression risk with snapshots.

Community
Intermediate
Alex1980AlexAlex1980Alex

graph-operations

Construct knowledge graphs from document chunks and query them with LightRAG/GraphRAG modes.

Community
Advanced
zircotezircote
20

mnemonic

Store and retrieve semantic, episodic, and procedural memories in filesystem namespaces.

Community
Intermediate
librefanglibrefang
10

vector-db

Design and optimize vector search systems for embedding-based retrieval.

Official
Advanced