memory-engine

Gate agent memory inputs and retrieval using structured memory architecture.

12|2|Updated Feb 14, 2026
One-click install
npx skills add https://github.com/CoworkedShawn/openclaw-skills --skill memory-engine-coworkedshawn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-engine
Source: https://github.com/CoworkedShawn/openclaw-skills/tree/main/memory-engine
Command: npx skills add https://github.com/CoworkedShawn/openclaw-skills --skill memory-engine-coworkedshawn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Memory management for autonomous agents requires structured gating, persistence, and recoverable context across runs and model changes. The Memory Engine provides a standardized architecture for gating inputs, loading relevant context, and running procedural runbooks.

Core Features & Use Cases

  • Memory gating and hierarchical memory (active-context, daily notes, and long-term MEMORY.md)
  • Runbooks for repeatable tasks and model switch continuity
  • Automated state detection, decay, and synchronization to keep context accurate

Quick Start

Load the memory engine, gate new input to active-context.md, and execute the appropriate runbooks for your current task.

Frequently Asked Questions about memory-engine

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

FAQPage Schema
How do I gate and govern agent memory for autonomous workflows?

Agent memory gating requires a structured architecture that controls what enters memory and what is retrieved, using active-context, daily notes, long-term MEMORY.md, and runbooks with policy-driven retention.

What is the best way to manage autonomous agent context across model changes?

Managing agent context across model changes uses runbooks for repeatable tasks and continuity, storing recoverable context in hierarchical memory layers with automated state detection and synchronization.

How does memory decay and state detection work for autonomous agents?

Memory decay and state detection work through automation hooks that monitor context accuracy, applying policy-driven retention rules to keep active-context and long-term MEMORY.md synchronized without manual intervention.

Do I need external dependencies to set up agent memory gating and runbooks?

Agent memory gating and runbooks require minimal external dependencies beyond Node-based scripts, integrating with active-context, TOOLS.md, and cron or state detectors for automated synchronization.

When should I use hierarchical memory architecture instead of flat context files?

Hierarchical memory architecture is needed when autonomous agents require structured gating, persistence, and recoverable context across multiple runs, separating active-context, daily notes, and long-term MEMORY.md layers.

Can I automate runbook execution and memory synchronization with cron?

Runbook execution and memory synchronization can be automated using cron and state detectors, triggering decay rules and context updates to keep working memory and long-term MEMORY.md accurate across runs.