Semantic Memory

What This Does

Give your AI agents a brain that learns and remembers:

• 🧠 Semantic Search: Find patterns by meaning, not keywords
• 💾 Three Memory Types: Semantic (forever), Episodic (90 days), Procedural (forever)
• 📈 Intelligence Compounds: Learn from every task, recall before you act
• 🔄 Auto-Consolidation: Promotes validated patterns automatically

Quick Start

Install

claude mcp add memory -- npx -y github:Sceat/semantic-memory-mcp

Then configure environment variables in ~/.claude.json:

{
  "mcpServers": {
    "memory": {
      "env": {
        "REDIS_URL": "redis://localhost:6379/0",
        "OPENAI_API_KEY": "your-openai-key-here"
      }
    }
  }
}

Use

Six tools available immediately:

• store_pattern - Save what you learned
• search_patterns - Find similar patterns
• set_reminder - Never forget important details
• check_reminders - Get context before tasks
• consolidate_memories - Promote validated patterns
• health_check - Verify system status

How It Works

┌─────────────────────────────────────────────────────┐
│                                                     │
│   Before Task: Query memory for similar patterns   │
│                Check reminders for this task type   │
│                                                     │
│   During Task: Execute with learned context        │
│                                                     │
│   After Task:  Store what you learned              │
│                Set reminders for next time          │
│                                                     │
│   Result: Intelligence compounds over time          │
│                                                     │
└─────────────────────────────────────────────────────┘

Local Development

If you want to develop or modify the server:

git clone https://github.com/Sceat/semantic-memory-mcp.git
cd semantic-memory-mcp
npm install

Then add to your Claude Code config:

{
  "mcpServers": {
    "memory": {
      "command": "node",
      "args": ["/path/to/semantic-memory-mcp/src/index.js"],
      "env": {
        "REDIS_URL": "redis://localhost:6379/0",
        "OPENAI_API_KEY": "your-openai-key-here"
      }
    }
  }
}

Requirements

• Node.js ≥ 18
• Redis 7.2+ with RediSearch module
• OpenAI API key
• Claude Code

License

MIT