mnemonics

Name: mnemonics
Availability: InStock
Author: Isaac

Store and recall persistent AI agent memories using markdown files with YAML frontmatter.

27|6|Updated Feb 3, 2026

Search Tags:#context management #knowledge base #ai agent #memory #persistence #historian

Ready to run

npx skills add https://github.com/5kahoisaac/opencode-configs --skill mnemonics-5kahoisaac

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mnemonics
Source: https://github.com/5kahoisaac/opencode-configs/tree/main/skills/mnemonics
Command: npx skills add https://github.com/5kahoisaac/opencode-configs --skill mnemonics-5kahoisaac

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the ephemeral nature of AI conversations by providing a robust mechanism for storing, recalling, and managing persistent memories across different interactions and sessions.

Core Features & Use Cases

Memory Storage: Create and update memories using various predefined types (e.g., architectural-decision, user-preference, learning).
Memory Retrieval: Search and recall relevant memories based on keywords or types.
Memory Management: Forget outdated memories and sync the memory index.
Use Case: When starting a new development session, recall all architectural-decision memories to ensure consistency with past choices.

Quick Start

Use the historian subagent to remember that we decided on PostgreSQL for the database.

Frequently Asked Questions about mnemonics

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

FAQPage Schema

How do I enable persistent memory for AI agents across different sessions?▼

Persistent memory for AI agents is enabled through a historian subagent that stores and recalls information across conversations using markdown files with YAML frontmatter and qmd indexing for retrieval.

What types of structured memories can AI agents store for software development?▼

AI agents can store structured memory types including architectural decisions, user preferences, learnings, and project conventions to maintain consistency across development sessions.

Can I recall specific past decisions when starting a new development session?▼

Yes, you can search and recall relevant memories based on keywords or types, allowing you to retrieve all architectural-decision memories at the start of a new session.

How do I manage outdated context or forget previous agent memories?▼

You can manage outdated context by using the memory management features to forget outdated memories and synchronize the memory index.

Does this persistent memory approach require any external dependencies?▼

No external dependencies are required to implement this persistent memory management, which relies on markdown files with YAML frontmatter for storage and qmd for indexing.

What is the best way to store architectural decisions for AI context management?▼

The best way to store architectural decisions is using the predefined architectural-decision memory type within the historian subagent, ensuring past choices are indexed for later retrieval.