mcpbeat Sign in

hmem — Humanlike Memory for AI Agents MCP Server

by bumblebiber Your server? Claim it
local only

hmem — Humanlike Memory for AI Agents runs on your own machine — the client starts it, so there is no endpoint to ping. 118 installs a week from npm. Last commit 21 Jul 2026.

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

Installs per day peak 126 · avg 20 · +27% w/w
a month agotoday
118
Installs / week
npm · hmem-mcp
24
Stars
0 open issues
21 Jul 2026
Last commit
no releases in 90 days
MIT
License
TypeScript

What the code does

We read the source, 5 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs a command on install [пакет] package.json:1
postinstall: node scripts/use-prebuild.cjs && node -e "try{require('child_process').execSync('node dist/cli.js update-skills',{stdio:'ignore'})}catch(e){}"
    const child = spawn(process.execPath, [process.argv[1], "sync", ...args], {
Dumps the whole environment hmem-reader.py:51
        env = dict(os.environ)
  <script src="https://cdn.sheetjs.com/xlsx-0.20.3/package/dist/xlsx.full.min.js" integrity="sha384-EnyY0/GSHQGSxSgMwaIPzSESbqoOLSexfnSMN2AP+39Ckmn92stwABZynq1JyzdT" crossorigin="anonymous"></script>

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add hmem-mcp -- npx -y hmem-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "hmem-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hmem-mcp"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.hmem-mcp]
command = "npx"
args = ["-y", "hmem-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "hmem-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hmem-mcp"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "hmem-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "hmem-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: HMEM_STORAGE_DIR (Directory where .hmem SQLite databases are stored. Defaults to ~/.hmem/).

Alternatives to hmem — Humanlike Memory for AI Agents

same job, measured the same way
MCP Memory
by germaniu

Local persistent memory for AI agents: SQLite + FTS5 (BM25) lexical search, zero external infra.

local only
dark-memory-mcp
by opita-code

Persistent memory + vibe-loop engine for AI agents. Single Go binary, SQLite-backed, stdio MCP.

179 installs/wk local only
Leteo
by asanabrial

Persistent memory for AI coding agents: one Rust binary, one local SQLite database.

118 installs/wk local only
agentmem
by oxgeneral

Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.

local only
Mnemon MCP
by nikitacometa

Persistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud.

47 installs/wk local only
Engram
by hbarefoot

Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.

53 installs/wk local only
repo-memory-mcp
by umarjaum

Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.

114 installs/wk local only
sync82
by oito2

Persistent, structured project memory for AI coding agents, stored locally in SQLite.

local only

hmem — Humanlike Memory for AI Agents — questions

Answers built from our own checks of this server.

Why is there no uptime for hmem — Humanlike Memory for AI Agents?
hmem — Humanlike Memory for AI Agents runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package hmem-mcp was installed 118 times last week.
How do I connect hmem — Humanlike Memory for AI Agents?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls hmem-mcp straight from npm; nothing to host, nothing to sign up for.
How many people use hmem — Humanlike Memory for AI Agents?
The npm package hmem-mcp was installed 118 times in the last week. Week over week that is +27%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is hmem — Humanlike Memory for AI Agents open source?
Yes — it is published under the MIT licence, written in TypeScript and 24 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.