cognitive-memory

Encode, consolidate, and recall information across multiple memory stores with decay and audit trails.

Updated Aug 23, 2026

Search Tags:#audit #multi-agent #memory #reflection #knowledge-graph #decay #memory-system

Ready to run

npx skills add https://github.com/xintuchain/tongtong --skill cognitive-memory-xintuchain

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Cognitive Memory System provides a robust, human-like memory architecture for agents, enabling multi-store encoding, consolidation, decay, recall, and audit trails across personal and multi-agent contexts.

Core Features & Use Cases

Core memory with episodic, semantic, procedural, and vault stores, plus decay-based relevance scoring and audit trails.
Trigger-driven memory routing and sleep-time reflection to improve long-term understanding and accountability in multi-agent environments.
Graph-based knowledge representation and audit-ready history for governance and compliance across teams.

Quick Start

Start by initializing memory, enabling search across stores, and adding agent instructions to AGENTS.md for memory triggers.

Frequently Asked Questions about cognitive-memory

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

FAQPage Schema

How do I implement an agent memory system with decay and audit trails?▼

A multi-agent memory system with audit trails encodes information across episodic, semantic, procedural, and vault stores, applying decay-based relevance scoring and logging mutations to track recall history. You initialize core memory, configure trigger-driven routing, and enable sleep-time reflection to consolidate context.

What is sleep-time reflection in a multi-agent memory architecture?▼

Sleep-time reflection in a multi-agent memory architecture is a consolidation process that reviews and reinforces stored information during inactive periods. It improves long-term understanding and accountability by updating knowledge graphs and decay scores without interrupting active agent operations.

How do I set up trigger-driven memory routing for multi-agent collaboration?▼

Trigger-driven memory routing for multi-agent collaboration is set up by adding agent instructions to AGENTS.md and configuring memory triggers. This routes information to the appropriate memory stores, enabling agents to access consolidated knowledge and audit-ready history during collaborative tasks.

Does this memory system support knowledge graph representation for governance?▼

Yes, the memory system supports graph-based knowledge representation for governance and compliance. It maintains audit-ready history by tracking mutations across memory stores, enabling teams to review recall paths and ensure accountability in multi-agent environments.

Do I need Python and Git to use a cognitive memory architecture with decay scoring?▼

Yes, you need Python3, Git, and Bash to use this cognitive memory architecture. These dependencies support the scripts and assets required to initialize memory stores, configure decay scoring, and maintain the event log and audit mechanism for tracking mutations.

What's the best way to prevent memory bloat in long-running multi-agent systems?▼

The best way to prevent memory bloat in long-running multi-agent systems is applying decay-based relevance scoring alongside sleep-time reflection. This architecture automatically consolidates necessary information and reduces the relevance of outdated data across episodic, semantic, and procedural stores while preserving an audit trail.