tiered-memory

Name: tiered-memory
Availability: InStock
Author: doggyhu

Manage and retrieve information from a three-tier memory system using Python scripts and LLM reasoning.

Updated Aug 27, 2026

Search Tags:#metrics #LLM #multi-agent #consolidation #distillation #memory system #structured metadata #memory completeness #critical sync

Ready to run

npx skills add https://github.com/DoggyHU/pipipax_claw_backup --skill tiered-memory-doggyhu

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tiered-memory
Source: https://github.com/DoggyHU/pipipax_claw_backup/tree/main/skills/tiered-memory
Command: npx skills add https://github.com/DoggyHU/pipipax_claw_backup --skill tiered-memory-doggyhu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, urllib, libsql_client, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the management and reasoning of a three-tier memory system for AI agents, saving time and reducing cognitive load.

Core Features & Use Cases

Memory System Management: Manages a tiered memory system (hot, warm, cold) to store and retrieve information efficiently.
LLM-Powered Retrieval: Uses LLM reasoning for semantic search and retrieval of relevant information.
Distillation Engine: Compresses conversations into structured facts and generates summaries.
Structured Metadata Extraction: Extracts URLs, commands, and file paths from text for enhanced search capabilities.
Memory Completeness Validation: Ensures daily notes are complete and actionable.
Consolidation Modes: Provides quick, daily, monthly, and full consolidation modes for memory maintenance.
Critical Sync: Synchronizes hot state and tree index to cloud for disaster recovery.
Metrics & Observability: Tracks memory system metrics and provides observability for performance analysis.
Multi-Agent Support: Supports multiple agents with scoped data and operations.
Integration with OpenClaw: Seamlessly integrates with OpenClaw for enhanced agent functionality.

Quick Start

Run the memory_cli.py script to manage and interact with the memory system.

Frequently Asked Questions about tiered-memory

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

FAQPage Schema

How does a tiered memory system for AI agents work?▼

A tiered memory system organizes agent knowledge into hot, warm, and cold storage tiers to optimize retrieval. It uses LLM semantic reasoning to retrieve relevant information and compresses conversations into structured facts.

How do I automate memory consolidation and distillation for multi-agent workflows?▼

You can automate memory consolidation by running Python scripts that use a distillation engine to compress conversations into structured facts. It supports quick, daily, monthly, and full consolidation modes to maintain memory across multiple scoped agents.

Do I need Turso and an LLM endpoint to use automated agent memory management?▼

Yes, automated agent memory management requires Python 3.8+, a Turso database for cold storage, and an LLM endpoint for semantic reasoning. These dependencies are necessary to execute the retrieval and distillation scripts.

What is the best way to extract structured metadata like URLs and commands from agent conversations?▼

The best way to extract structured metadata is to use a distillation engine that identifies and parses URLs, commands, and file paths from text. This enhances semantic search capabilities within the agent memory system.

How do I synchronize hot state memory and tree indexes for disaster recovery?▼

You synchronize hot state memory and tree indexes using the critical sync feature, which pushes this data to cloud storage. This ensures data consistency and provides disaster recovery for multi-agent systems.

Can I track memory system metrics and observability for multiple AI agents?▼

Yes, you can track memory system metrics and observability for multiple AI agents with scoped data operations. The system provides built-in tracking to analyze retrieval performance and memory completeness validation.