cognitive-memory

Overview

The Cognitive Memory System is an intelligent multi-store memory system that mimics human-like encoding, consolidation, decay, and recall. It’s designed to replace basic flat-file memory with a cognitive architecture featuring episodic, semantic, procedural, and core memory stores.

Key Features

• Multi-store memory with natural language triggers, knowledge graphs, decay-based forgetting, reflection consolidation, philosophical evolution, multi-agent support, and full audit trail.
• Supports shared read, gated write access model for multi-agent systems.
• Includes philosophical meta-reflection that deepens understanding over time.
• Covers MEMORY.md, episode logging, entity graphs, decay scoring, reflection cycles, evolution tracking, and system-wide audit.

How It Works

The Cognitive Memory System uses a combination of natural language triggers, knowledge graphs, and decay-based forgetting to manage memory. It also includes a reflection consolidation process that deepens understanding over time.

Use Cases

• Setting up agent memory
• Configuring remember/forget triggers
• Enabling sleep-time reflection
• Building knowledge graphs
• Adding audit trails