Agent skill

memory-keeper

Persistent context/memory management MCP server. Stores and retrieves context across AI sessions.

View SKILL.md on GitHub Repository
Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/memory-keeper-disabled

Metadata

Additional technical details for this skill

clawdbot 
{
    "emoji": "\ud83e\udde0",
    "requires": {
        "env": [
            "MEMORY_KEEPER_PATH"
        ]
    },
    "installed": "\u2705 Installed via npm"
}

SKILL.md

Memory Keeper - Persistent Context

Persistent context management that stores and retrieves information across AI sessions.

Status

✅ INSTALLED via npm

bash
npm install -g mcp-memory-keeper
which mcp-memory-keeper  # /home/opc/.nvm/versions/node/v22.20.0/bin/mcp-memory-keeper

Setup

Environment variables:

bash
# Path to store memory database
export MEMORY_KEEPER_PATH="/home/opc/.clawdbot/memory-keeper"

# Optional: encryption key
export MEMORY_KEEPER_KEY="your-encryption-key"

Usage

Run as MCP Server

bash
# As MCP server (for integration with agents)
memory-keeper --transport stdio

# With custom storage path
memory-keeper --storage /path/to/memory.db

Using the CLI

bash
uv run {baseDir}/scripts/memory-keeper.py store "key" "value"
uv run {baseDir}/scripts/memory-keeper.py retrieve "key"
uv run {baseDir}/scripts/memory-keeper.py search "query"
uv run {baseDir}/scripts/memory-keeper.py list
uv run {baseDir}/scripts/memory-keeper.py delete "key"

Commands

Store Information

bash
# Store a fact
uv run scripts/memory-keeper.py store "user_preference" "Bradley likes concise messages"

# Store context from a session
uv run scripts/memory-keeper.py store "session_2026_01_13" "Discussed MCP servers, installed context7 and memory-keeper"

Retrieve Information

bash
# Get stored information
uv run scripts/memory-keeper.py retrieve "user_preference"

# Search memories
uv run scripts/memory-keeper.py search "MCP"

# List all memories
uv run scripts/memory-keeper.py list

Delete

bash
uv run scripts/memory-keeper.py delete "old_memory"

When to Use

Task Use This Alternative
Remember across sessions Memory Keeper Manual file updates
Store user preferences Memory Keeper SECRETS.md
Track context between sessions Memory Keeper Memory files
Quick lookup Memory Keeper qmd search

Architecture

Session → Store Context → Persistent DB → Retrieve → Next Session

Comparison

Feature Memory Keeper Current (Files)
Cross-session memory ✅ Yes ❌ Manual
Automatic storage ✅ Yes ❌ Manual
Searchable ✅ Yes ✅ qmd
Structured ✅ Yes ❌ Unstructured
Fast lookup ✅ Yes ⚠️ Slow

Notes

  • Stores data locally (SQLite by default)
  • Supports encryption for sensitive data
  • Can export/import memories
  • Works offline

Files

  • scripts/memory-keeper.py - CLI wrapper
  • MCP server: memory-keeper
  • Storage: ~/.clawdbot/memory-keeper/ (default)

See Also

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

majiayu000/claude-skill-registry

agent-ops-spec

Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-state

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-spec

Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-testing

Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-testing

Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-state

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

163 31
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results