kata-agent-memory-design

Official

Design a safe 3-layer agent memory.

Authorguardiatechnology
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It helps teams define an agent memory architecture that is practical for operations while staying compliant with retention and privacy requirements.

Core Features & Use Cases

  • 3 mandatory memory layers: short (session window), medium (per-tenant client history), and long (shared, stable knowledge).
  • Explicit TTL and retention policies: maps retention to a reference file and enforces right-sizing by event classes.
  • PII-safe handling and deletion workflows: mandates redaction for persistence, anonymization for ingestion, and a defined right-to-be-forgotten API with an SLA.

Quick Start

Ask an AI to generate docs/{context}/agents/{agent}/memory.md by filling in short, medium, and long layer schemas plus retention and deletion details for {agent} within the {context} bounded scope.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: kata-agent-memory-design
Download link: https://github.com/guardiatechnology/design-system/archive/main.zip#kata-agent-memory-design

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.