A persistent memory system that stores observations and learnings in a single file: .claude/mind.mv2.

How do I search memories?

Use the Node.js script at CLAUDE_PLUGIN_ROOT/dist/scripts/find.js with a query and optional limit to retrieve results.

Where is the memory file stored?

In .claude/mind.mv2; it is portable and Git-friendly for easy sharing.

mind

Scanned

npx machina-cli add skill memvid/claude-brain/mind --openclaw

Files (1)

SKILL.md

2.2 KB

Claude Mind

You have access to a persistent memory system powered by Claude Mind. All your observations, discoveries, and learnings are stored in a single .claude/mind.mv2 file.

How to Execute Memory Commands

Use the bundled SDK scripts via Node.js (NOT the CLI). The scripts are at ${CLAUDE_PLUGIN_ROOT}/dist/scripts/.

Search Memories

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "<query>" [limit]

Examples:

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "authentication" 5
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "database schema" 10

Ask Questions

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "<question>"

Examples:

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "Why did we choose React?"
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "What was the CORS solution?"

View Statistics

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/stats.js"

View Recent Memories

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/timeline.js" [count]

Memory Types

Memories are automatically classified into these types:

discovery - New information discovered
decision - Important decisions made
problem - Problems or errors encountered
solution - Solutions implemented
pattern - Patterns recognized in code/data
warning - Warnings or concerns noted
success - Successful outcomes
refactor - Code refactoring done
bugfix - Bugs fixed
feature - Features added

File Location

Your memory is stored at: .claude/mind.mv2

This file is:

Portable - Copy it anywhere, share with teammates
Git-friendly - Commit to version control
Self-contained - Everything in ONE file
Searchable - Instant semantic search

Usage Tips

Start of session: Recent memories are automatically injected as context
During coding: Observations are captured automatically from tool use
Searching: Use natural language queries to find relevant past context
Sharing: Send the .mind.mv2 file to teammates for instant onboarding

Source

git clone https://github.com/memvid/claude-brain/blob/main/skills/mind/SKILL.mdView on GitHub

Overview

Claude Mind is a persistent memory system that stores all observations, discoveries, and learnings in a single .claude/mind.mv2 file. It enables fast, semantic search, Q&A, and a memory timeline to help you reflect and build on past work. Access is via bundled Node.js scripts, making it portable and easy to share.

How This Skill Works

Memories are automatically categorized into types such as discovery, decision, problem, solution, and more, all stored in mind.mv2. Interact with the memory via Node.js scripts located at CLAUDE_PLUGIN_ROOT/dist/scripts (find.js for search, ask.js for questions, stats.js for statistics, timeline.js for recent memories). The file is portable, Git-friendly, and self-contained for easy movement and onboarding.

When to Use It

When you need to recall past observations or decisions relevant to current work
When you want quick, natural-language answers about previous contexts
When you need statistics or a snapshot of memory activity
When collaborating—share the mind.mv2 file to onboard teammates
When reviewing patterns, warnings, or refactors stored over time

Quick Start

Step 1: Confirm CLAUDE_PLUGIN_ROOT is set and the mind file exists at .claude/mind.mv2
Step 2: Run a search with the memory script, e.g., CLAUDE_PLUGIN_ROOT/dist/scripts/find.js <query> [limit]
Step 3: Explore results or run additional commands like ask.js or timeline.js as needed

Best Practices

Keep the mind.mv2 file in a version-controlled repository to track changes
Use natural-language queries to maximize semantic search effectiveness
Rely on memory types (discovery, decision, problem, solution, etc.) to organize entries
Regularly review the timeline to stay updated with recent memories
Limit query scope when exploring large memories to improve relevance

Example Use Cases

Search for 'authentication' to surface related memories
Ask why a technology choice was made (e.g., 'Why did we choose React?')
View the latest memories with timeline.js to review recent work
Share the .mind.mv2 file with a teammate for quick onboarding
Analyze memory statistics to identify patterns or gaps

Frequently Asked Questions

Add this skill to your agents