hmem — Humanlike Memory for AI Agents

Overview

hmem — Humanlike Memory for AI Agents is a Model Context Protocol (MCP) server: Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded. As an MCP server it plugs straight into AI assistants, exposing its functionality as tools the model can invoke on your behalf.

It runs locally: the npm package hmem-mcp speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v1.6.7, published under the MIT license, with source at Bumblebiber/hmem on GitHub, where it has earned 24 stars.

You'll find hmem — Humanlike Memory for AI Agents in the AI & Agents category here on mcp.site; it connects to Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and any other MCP client — see the install snippets below. If you maintain hmem — Humanlike Memory for AI Agents for Bumblebiber, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "hmem_humanlike_memory_for_ai_agents": {
      "command": "npx",
      "args": [
        "-y",
        "hmem-mcp"
      ]
    }
  }
}