shared-memory

Save and load cross-session context under .claude/memory/sessions.

Updated Feb 2, 2026
One-click install
npx skills add https://github.com/forrany/Agent-configs --skill shared-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shared-memory
Source: https://github.com/forrany/Agent-configs/tree/main/bundles/shared-memory/.cursor/skills/shared-memory
Command: npx skills add https://github.com/forrany/Agent-configs --skill shared-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides cross-session memory management for AI assistants, enabling retention of important context across conversations and prompting memory saves or loads at appropriate times.

Core Features & Use Cases

  • Cross-session memory awareness: retain key details across chats and tasks and prompt users to save or load memories when needed.
  • Local memory storage and referencing: store memories under the project root at .claude/memory/sessions for quick recall across sessions.
  • Use Case: When managing a long-running project, the AI recalls prior decisions and milestones to guide current work.

Quick Start

Use the memory commands to save and load context between sessions. Save a milestone with /save-session, load with /load-session, and reference memories via @.claude/memory/sessions/NAME.md.

Frequently Asked Questions about shared-memory

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

FAQPage Schema
How do I preserve AI context across multiple chat sessions?

Cross-session memory management preserves AI context by saving and loading important details under the .claude/memory/sessions directory. You can save milestones with /save-session and reload them later to maintain continuity across conversations.

How does cross-session memory loading work for long-running tasks?

Cross-session memory loading works by storing project milestones and decisions as local markdown files. The AI references these saved memories via @claude/memory/sessions/NAME.md to recall prior context and guide current work.

When do I need to save context for AI continuity?

You need to save context for AI continuity when managing long-running tasks or multi-session work where important details must be retained. The AI prompts you to save or load memories at appropriate times to prevent context loss.

What is the best way to manage AI memory for multi-session projects?

The best way to manage AI memory for multi-session projects is using local memory commands to save and load context. Save session milestones with /save-session and load prior context with /load-session to retain key decisions.

Do I need any external dependencies to enable cross-session memory?

No external dependencies are required to enable cross-session memory. The skill operates independently, storing and referencing memory files locally within your project root at .claude/memory/sessions.

Can I use local memory storage for AI assistants without external integrations?

Yes, you can use local memory storage for AI assistants without external integrations. The skill stores memories directly under the project root at .claude/memory/sessions for quick recall across sessions.