One-click install
npx skills add https://github.com/brobertsaz/claude-os --skill memory-brobertsaz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/brobertsaz/claude-os/tree/main/templates/skills/memory
Command: npx skills add https://github.com/brobertsaz/claude-os --skill memory-brobertsaz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI assistants often lack persistent memory, forcing you to repeat context, decisions, and insights across different sessions. This Skill provides your AI with a dedicated, searchable memory that endures, eliminating repetitive explanations.

Core Features & Use Cases

  • Instant Recall: Quickly save and retrieve technical insights, project context, debugging solutions, and architectural decisions with simple commands.
  • Automatic Context Loading: Your AI assistant automatically references relevant memories at the start of new sessions, ensuring it's always up-to-date without you having to prompt it.
  • Searchable Archive: All memories are timestamped, tagged, and full-text searchable, making it easy to find past information when you need it.
  • Use Case: At the end of a coding session, tell Claude "Save to memory: We refactored the user authentication module to use OAuth2. Next, implement refresh tokens." Claude will remember this for your next session, allowing you to pick up exactly where you left off.

Quick Start

Remember: The new API endpoint for user profiles is /api/v1/users/{id} and requires an Authorization header.

Frequently Asked Questions about memory

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

FAQPage Schema
How do I save and recall information across AI sessions?

Session memory stores important information like project context, debugging solutions, and architectural decisions, then automatically retrieves relevant entries when you start a new session. Use prompts like 'Remember:' or 'Save to memory:' to capture data with timestamps and tags for searchable recall.

Can I search through past technical insights and project decisions?

All saved memories are timestamped, tagged, and full-text searchable, letting you quickly find past technical insights, architectural decisions, and project context without repeating explanations across sessions.

What information should I store in persistent memory?

Store yesterday's work context, debugging solutions, architectural decisions, API endpoints, technical insights, and quick facts—anything you'd otherwise need to re-explain or re-document when resuming a project in a new session.

How does automatic context loading work at the start of a session?

Your AI assistant automatically references relevant saved memories at session start based on your current task, eliminating the need to manually restate prior decisions, project history, or technical context you've already documented.

Does persistent memory work across different AI assistants or projects?

Memory entries are stored with titles, content, tags, and timestamps in the Memory MCP, enabling consistent recall across sessions within your AI workflow—ideal for multi-session projects requiring knowledge retention and context continuity.