memory-manager

Manage persistent memory across AI sessions using structured markdown notes.

Updated Feb 8, 2026
One-click install
npx skills add https://github.com/dundas/uhr --skill memory-manager-dundas
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-manager
Source: https://github.com/dundas/uhr/tree/main/.claude/skills/memory-manager
Command: npx skills add https://github.com/dundas/uhr --skill memory-manager-dundas

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill manages and maintains persistent context across AI sessions, ensuring continuity of knowledge and user preferences.

Core Features & Use Cases

  • Multi-Layered Memory: Organizes information into daily notes, long-term knowledge, and optional semantic indexes.
  • Contextual Awareness: Enhances AI responses by recalling past interactions, user preferences, and project details.
  • Use Case: An AI assistant can remember a user's preferred communication style and project details from previous conversations, leading to more personalized and efficient interactions.

Quick Start

Use the memory-manager skill to remember the current project details.

Frequently Asked Questions about memory-manager

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

FAQPage Schema
How do I maintain persistent memory for an AI agent across different sessions?

You can maintain persistent memory by using a multi-layered approach that logs daily notes, curates long-term knowledge, and applies semantic indexing for retrieval. This ensures AI agents retain context across different sessions.

What is the best way to make an autonomous AI agent remember user preferences?

Making an AI agent remember user preferences involves curating long-term knowledge and maintaining contextual awareness through structured markdown logging. This allows the agent to recall past interactions and project details efficiently.

How do I log and retrieve project context using structured markdown for AI knowledge management?

Logging and retrieving project context for AI knowledge management requires structured markdown for logging operations and semantic indexing for retrieval. This supports maintaining specific project details and continuous contextual awareness.

Can I use semantic indexing to retrieve long-term knowledge for my AI assistant?

Yes, you can use semantic indexing to retrieve long-term knowledge for an AI assistant. This multi-layered memory approach organizes information into daily notes and long-term knowledge, ensuring efficient retrieval of past interactions.

Do I need structured markdown to manage context persistence for AI agents?

Yes, structured markdown is required to manage context persistence for AI agents. It provides the necessary format for logging operations and retrieving information across daily notes and long-term knowledge layers.