Hmem — Humanlike Memory For AI Agents MCP Server

Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.

Local serverstdioTypeScript

What is the Hmem — Humanlike Memory For AI Agents MCP server?

Hmem — Humanlike Memory For AI Agents MCP server exists for a simple reason — assistants are far more useful when they can act on Hmem — Humanlike Memory For AI Agents directly instead of describing what you should do. Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.

What you get

One load_project() call. ~3000 tokens. Your agent knows everything important about a project — every past mistake, every decision, every open task — across sessions, devices, and AI providers. No setup per conversation. No "let me re-read the codebase." It just remembers.

Setting it up

The server ships on npm as hmem, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Hmem — Humanlike Memory For AI Agents is connected, these are the calls the assistant has available:

  • Curation — The Curation tool exposed by this server
  • Announcements — The Announcements tool exposed by this server

Configuration and credentials

You will need 6 environment variables: HMEM_PROJECT_DIR, HMEM_AGENT_ID, HMEM_PATH, DEEPSEEK_API_KEY, ANTHROPIC_API_KEY, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the hmem — humanlike memory for ai agents mcp server does with a few real requests.

Choosing this one

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Hmem — Humanlike Memory For AI Agents's toolset — Curation, Announcements — is a fair guide to whether it matches your workflow. It is maintained by Bumblebiber; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Hmem — Humanlike Memory For AI Agents's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
CurationThe Curation tool exposed by this server.
AnnouncementsThe Announcements tool exposed by this server.

How to install the Hmem — Humanlike Memory For AI Agents MCP server

{
  "mcpServers": {
    "hmem": {
      "command": "/absolute/path/to/node",
      "args": ["/absolute/path/to/hmem/dist/mcp-server.js"],
      "env": { "HMEM_PROJECT_DIR": "/home/yourname/.hmem" }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
HMEM_PROJECT_DIRFilesystem location the server is allowed to use.Optional
HMEM_AGENT_IDConfiguration value read at startup.Optional
HMEM_PATHFilesystem location the server is allowed to use.Optional
DEEPSEEK_API_KEYCredential the server authenticates with.Yes
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Hmem — Humanlike Memory For AI Agents to Curation.
  • Use Hmem — Humanlike Memory For AI Agents to Announcements.

Frequently asked questions

It connects Hmem — Humanlike Memory For AI Agents to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Curation, Announcements) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Hmem — Humanlike Memory For AI Agents directly.