memory-manager

Organize AI agent memory into episodic, semantic, and procedural layers.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/binfen1/my-skills --skill memory-manager-binfen1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-manager
Source: https://github.com/binfen1/my-skills/tree/main/openclaw/memory-manager
Command: npx skills add https://github.com/binfen1/my-skills --skill memory-manager-binfen1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents often lose context as tasks evolve. This Skill provides a three-tier memory architecture (episodic, semantic, procedural) with compression detection and automatic organization to maintain long-term context and improve retrieval.

Core Features & Use Cases

  • Episodic: capture time-based events to reconstruct sequences of actions.
  • Semantic: extract knowledge and facts for quick recall and reasoning.
  • Procedural: store repeatable workflows for consistent execution and automation.
  • Use Case: keep an agent's memory healthy during long-running missions, detect compression risk, and generate context-preserving snapshots.

Quick Start

Initialize memory structure and start health checks with the provided scripts.

Frequently Asked Questions about memory-manager

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

FAQPage Schema
How do I preserve AI context during long-running agent workflows?

To preserve AI context, organize agent memory into episodic, semantic, and procedural layers with compression detection and auto-snapshots. This three-tier architecture maintains long-term context and enables efficient retrieval during long-running missions.

What is three-tier memory architecture for AI agents?

Three-tier memory architecture organizes AI agent context into episodic for time-based events, semantic for extracted facts, and procedural for repeatable workflows. This structure maintains high-context performance and enables efficient knowledge retrieval.

How do I detect memory compression risk in agent context management?

Detect memory compression risk by monitoring agent memory health through automated checks. The system identifies when context limits approach capacity and generates automatic snapshots to preserve knowledge before degradation occurs.

How do I capture and retrieve episodic memory for AI workflows?

Capture episodic memory by logging time-based events to reconstruct action sequences, then retrieve them through semantically-indexed search. This preserves the chronological context needed for reproducible agent workflows.

Does this agent memory organization require external knowledge-graph dependencies?

No external dependencies are required. The memory organization enforces a three-tier structure with compression detection and semantically-indexed search internally, maintaining high-context performance without additional knowledge-graph modules.