memory

Manage semantic memory records across Claude Code projects via a JSON interface.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/orenmagid/claude-cabinet --skill memory-orenmagid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/orenmagid/claude-cabinet/tree/main/templates/skills/memory
Command: npx skills add https://github.com/orenmagid/claude-cabinet --skill memory-orenmagid

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Expose and manage semantic memory for Omega across Claude Code projects. This capability helps teams track decisions, lessons, preferences, and constraints so context persists across sessions and sessions start with continuity.

Core Features & Use Cases

  • Browse and search memories across a project with filters and tags
  • Remember decisions, lessons, preferences, and constraints
  • Forget or delete memories to keep the knowledge graph relevant
  • Use cases: audit project history, surface decisions during planning, and reason about past outcomes

Quick Start

Ask Omega to list memories for this project.

Frequently Asked Questions about memory

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

FAQPage Schema
How do I maintain semantic memory across Claude Code projects?

You maintain semantic memory by using a memory adapter that reads and writes memory records via a JSON interface. This tracks decisions, lessons, and constraints so project context persists across sessions.

What is semantic memory management for AI coding sessions?

Semantic memory management is the process of storing and retrieving project knowledge like decisions and constraints. It exposes a JSON interface to browse, search, and remember context across AI sessions.

How do I browse and search past project memories and decisions?

You browse and search past project memories by applying filters and tags to the memory records. This surfaces stored decisions, lessons, and preferences for reasoning about past outcomes during planning.

Can I delete or forget outdated memories to keep the knowledge graph relevant?

Yes, you can forget or delete outdated memories to keep the knowledge graph relevant. This removes stale constraints and preferences, ensuring the semantic memory remains accurate for current project needs.

Do I need YAML frontmatter to manage project memory?

Yes, you need YAML frontmatter containing the name and description to manage project memory. This metadata is required by the Python-based memory adapter to properly read and write memory records.