memory

Read and update persistent memory files for Claude across projects and sessions.

2|1|Updated Jul 26, 2025
One-click install
npx skills add https://github.com/ImpactMojo/ImpactMojo --skill memory-impactmojo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/ImpactMojo/ImpactMojo/tree/main/.claude/skills/memory
Command: npx skills add https://github.com/ImpactMojo/ImpactMojo --skill memory-impactmojo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Claude users need a reliable way to maintain persistent context across projects and sessions, reducing repeated input and preserving key decisions, notes, and state.

Core Features & Use Cases

  • Read global memory at ~/.claude/memory.md and project memory at .claude/memory.md for cohesive context.
  • Remember, update, or forget memory entries to capture decisions, bugs, and project state.
  • Sync memory at session boundaries to keep continuity across tasks and conversations.

Quick Start

Remember the key decision to store project-specific notes in .claude/memory.md and global preferences in ~/.claude/memory.md.

Frequently Asked Questions about memory

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

FAQPage Schema
How do I keep persistent context across Claude projects and sessions?

Persistent context is managed by reading and writing notes to memory.md files, capturing decisions, bugs, and state so you don't need to repeat inputs across sessions.

Can I save project-specific notes separately from global preferences?

Yes, project memory is stored in .claude/memory.md while global preferences are stored in ~/.claude/memory.md, allowing you to separate project-specific context from broader settings.

What's the best way to sync session logs and state changes for research workflows?

Syncing session logs and state changes is handled at session boundaries, updating memory files to maintain continuity across collaborative tasks and conversations.

How does categorizing memory entries into sections for decisions and bugs work?

Memory entries are categorized into dedicated sections for decisions, bugs, and state changes, organizing notes so specific context can be read, updated, or forgotten as needed.

Do I need any dependencies to manage persistent notes for product development?

No dependencies are required to manage persistent notes, as the memory operations read and write directly to local memory.md files for product development workflows.