MCP Directory

Cartisien/engram-mcp

GitHub
Productivity

Persistent semantic memory for AI agents. SQLite-backed, local-first, zero config. Semantic search via Ollama embeddings (nomic-embed-text) with keyword fallback. remember, recall, history, forget, and stats tools. Works with Claude Desktop, Cursor, and any MCP client.

Direct install

Run the underlying MCP server directly — without Agent-CoreX routing.

npx -y engram-mcp

Use with Agent-CoreX

Agent-CoreX intelligently routes which tools from Cartisien/engram-mcp your AI agent actually needs per request — reducing token usage and cost.

agent-corex.json

{
  "mcpServers": {
    "engram-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "engram-mcp"
      ]
    }
  }
}

Route Cartisien/engram-mcp intelligently

Connect in 2 minutes. Only pay for the tools your agent actually uses.

Installation Guide

Use with Agent-CoreX

Recommended: intelligent tool routing, lower costs

uvx agent-corex mcp add engram-mcp

Agent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.

Direct Install

Use Cartisien/engram-mcp directly without routing

npx -y engram-mcp

New to Agent-CoreX? View setup guide →

Cartisien/engram-mcp MCP Server — Agent-CoreX