memo MCP Server

by jagoff Your server? Claim it

local only

memo runs on your own machine — the client starts it, so there is no endpoint to ping. 2 685 installs a week from pypi. Last commit 1 Sep 2026.

Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.

Installs per day peak 1 208 · avg 491 · -50% w/w

a month agotoday

2 685

Installs / week

pypi · mlx-memo

Stars

0 open issues

1 Sep 2026

Last commit

0 releases in 90 days

MIT

License

Python

What the code does

We read the source, 18 h ago · rules 3dff92dd89df

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 an external command packaging/mcpb-node/bootstrap.js:87

  const child = spawn(

Builds a file path from a variable packaging/mcpb-node/bootstrap.js:38

      const candidate = path.join(directory, cmd + extension);

Runs an external command src/memo/claim_support.py:57, src/memo/cli_code_intel.py:45, src/memo/cli_dashboard.py:195 и ещё 63

        proc = subprocess.run(

Dumps the whole environment src/memo/eval_against.py:443, src/memo/journey_check.py:146, src/memo/runtime/agent_registry.py:106 и ещё 7

        env = dict(os.environ)

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.

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.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add memo -- uvx mlx-memo

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memo": {
      "args": [
        "mlx-memo"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.memo]
command = "uvx"
args = ["mlx-memo"]

.cursor/mcp.json

{
  "mcpServers": {
    "memo": {
      "args": [
        "mlx-memo"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "memo": {
      "args": [
        "mlx-memo"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to memo

same job, measured the same way

Mnemon MCP

by nikitacometa

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

54 installs/wk local only

KEPTA — Agent Memory

by damiantodorovic

Local memory for AI agents. One SQLite file on your machine — no cloud, no account.

729 installs/wk local only

Tdai Memory MCP

by tinhien11

Local-first MCP memory server for coding agents. No API key, no cloud. SQLite + FTS5 + sqlite-vec.

126 installs/wk local only

Memory Kernel

by artem362

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

122 installs/wk local only

Engram

by hbarefoot

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

82 installs/wk local only

Total Recall

by bas-more

Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.

71 installs/wk local only

Total Recall

by avi-bendetsky

Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.

local only

Memharness

by las7

Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.

38 installs/wk local only

memo — questions

Answers built from our own checks of this server.

Why is there no uptime for memo?

memo 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 pypi package mlx-memo was installed 2 685 times last week.

How do I connect memo?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls mlx-memo straight from pypi; nothing to host, nothing to sign up for.

How many people use memo?

The pypi package mlx-memo was installed 2 685 times in the last week. Week over week that is -50%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is memo open source?

Yes — it is published under the MIT licence, written in Python and 19 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.