A sophisticated 5-layer memory architecture that provides AI agents with persistent, cross-session continuity and automated task tracking.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install moore-pyramid-memory-system
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install moore-pyramid-memory-system using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Moore Pyramid Memory System?
The Moore Pyramid Memory System is a robust framework designed to solve the challenge of cross-session forgetting in AI agents. By utilizing a hierarchical 5-layer structure, it ensures that your agent retains essential project data, user preferences, and pending tasks indefinitely. This system transforms the agent from a stateless assistant into a continuous collaborator that understands the history and future goals of your workspace. As a cornerstone of advanced Openclaw Skills, it provides the structural backbone needed for complex, long-term project management and deep context retention.
Moore Pyramid Memory System Use Cases
- Tracking complex coding tasks that require multiple days or sessions to complete.
- Maintaining a permanent record of user preferences and project standards across different interactions.
- Automating the generation of weekly and monthly progress reports from daily activity logs.
- Ensuring that pending action items are never lost during session timeouts or network interruptions.
How Moore Pyramid Memory System Works
- Execution begins with the startup-read.js script, which automatically injects 5 layers of historical context into the agent's active memory.
- The agent checks the .todos.md file immediately to identify outstanding tasks from previous sessions.
- During the interaction, the agent records new developments and updates the cross-session todo list in real-time.
- When a conversation ends or a topic shifts, the system triggers an automatic summary process, writing the details to a daily diary file.
- Background cron jobs periodically run archiving scripts to synthesize daily logs into weekly and monthly summaries, optimizing the memory for long-term retrieval.
Moore Pyramid Memory System Setup
To implement this system within your Openclaw Skills environment, follow these installation steps:
- Copy the provided scripts to your local script directory:
cp scripts/*.js ~/.openclaw/workspace/scripts/
- Initialize the hierarchical directory structure in your workspace:
mkdir -p memory/weekly memory/monthly
touch MEMORY.md .todos.md
- Configure your system's crontab to handle automated archiving:
# Weekly review at 9AM every Monday
0 9 * * 1 node ~/.openclaw/workspace/scripts/weekly-archive.js
# Monthly review at 10AM on the last day of the month
0 10 28-31 * * [ $(date -d +1day +%d) -eq 1 ] && node ~/.openclaw/workspace/scripts/monthly-archive.js
Moore Pyramid Memory System Data Schema & Taxonomy
The system organizes data across five distinct layers to balance detail and longevity:
| Layer | File/Path | Content Type |
|---|---|---|
| Layer 1 | MEMORY.md |
Permanent core essence and high-level project goals. |
| Layer 2 | memory/monthly/ |
Synthesized monthly summaries for long-term recall. |
| Layer 3 | memory/weekly/ |
Weekly review files summarizing the current month's progress. |
| Layer 4 | memory/*.md |
Granular daily diaries covering the last 14 days of activity. |
| Layer 5 | .todos.md |
Critical cross-session task lists with 'Pending' and 'Completed' sections. |
Moore Pyramid Memory System Advanced Features
- Automated conversation summaries triggered by specific keywords or periods of inactivity.
- Multi-layer context loading that optimizes token usage by prioritizing recent or permanent data.
- Systematic archiving logic that prevents memory bloat while preserving essential project history.
- Seamless integration with other Openclaw Skills like MemOS for enhanced semantic search capabilities.
SKILL.md
Loading
Related Openclaw Skills
Agency Orchestrator
An intelligent multi-agent coordination system that automatically analyzes tasks and selects the best AI agents to collaborate on complex projects.
AVIC Information Assistant
A specialized assistant for querying products, news, financial data, and official resources for the Aviation Industry Corporation of China.
Chargeback Assistant
An automated expert system designed to help consumers navigate complex payment network reason codes and successfully file transaction disputes.
Prediction Market Watcher
A robust automation framework for tracking positions, scanning for opportunities, and executing trades on prediction markets like Kalshi and Polymarket.
Anomaly Detection
An automated diagnostic tool that identifies abnormal metric fluctuations by comparing real-time data against historical statistical baselines.
Arsenal FC
A dedicated AI agent skill for fetching real-time Arsenal FC statistics, news, and historical data.
Featured*
