Engram Memory

Verified Integration

Author: @spawning•Category: ServerApplication

GitHub Repository

JSON-RPC 2.0

Protocol Standard

Sub-second

Execution Latency

Active

Operational Status

Client Configuration

— Connect Engram Memory to Claude Desktop or Cursor in seconds

{
  "mcpServers": {
    "engram-memory-2": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-engram-memory-2"
      ],
      "env": {}
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).

Architecture & Capabilities

System Overview

Provides AI agents with persistent, self-hosted memory across sessions using a three-tiered recall engine.

Indexed Date

7/22/2026

License

Open Source

Protocol Layer

stdio / SSE RPC

Frequently Asked Questions

Architecture and operational details for Engram Memory

It employs a three-tiered recall engine: a Hot-Tier Cache for sub-millisecond lookups of frequently accessed memories, a Multi-Head Hash Index for O(1) candidate retrieval, and Hybrid Vector Search (Qdrant + BM25) for deep semantic understanding, optimizing speed and accuracy at scale.

Related MCP Servers

Browse all servers →

@configuring

0xArchive

Provides comprehensive historical and real-time crypto market data, including orderbooks, trades, candles, and more, from Hyperliquid, HIP-3, and Lighter.xyz.

MCP Server5 FAQs

Learn more

@spawning

0xGasless

Facilitates gasless blockchain transactions and interactions directly from Claude AI conversations.

MCP Server4 FAQs

Learn more

@spawning

0xGasless

Bridges Claude AI with blockchain networks, enabling gasless transactions, swaps, and transfers directly from natural language conversations.

MCP Server5 FAQs

Learn more