mcpbeat Sign in

Memory OS AI MCP Server

local only

Memory OS AI runs on your own machine — the client starts it, so there is no endpoint to ping. 58 installs a week from pypi. Last commit 3 Mar 2026.

Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking

Installs per day peak 20 · avg 9 · -23% w/w
a month agotoday
58
Installs / week
pypi · memory-os-ai
3
Stars
0 open issues
3 Mar 2026
Last commit
0 releases in 90 days
GPL-3.0
License
Python

What the code does

We read the source, 20 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.

Unsafe deserialization legacy/memory_os_ai.py:224
            embeddings = pickle.load(f)
Runs an external command legacy/memory_os_ai_gui.py:258
                subprocess.run(["xdg-open", chemin_fichier], check=True)
        chemin_fichier = os.path.join(DOSSIER_FICHIERS, self.selected_file)
        for root, _, files in os.walk(search_dir):

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 memory-os-ai -- uvx memory-os-ai
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "memory-os-ai": {
      "args": [
        "memory-os-ai"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.memory-os-ai]
command = "uvx"
args = ["memory-os-ai"]
.cursor/mcp.json
{
  "mcpServers": {
    "memory-os-ai": {
      "args": [
        "memory-os-ai"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "memory-os-ai": {
      "args": [
        "memory-os-ai"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to Memory OS AI

same job, measured the same way
Afterpaths
by burnssa

Session memory for AI coding agents. Search past sessions, extract rules, and track what works.

139 installs/wk local only
Agent Knowledge
by keshrath

Cross-session memory for AI agents - knowledge graph, scoring, semantic search

119 installs/wk local only
CLI
by aligndottech

Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.

647 installs/wk local only
MCP Memory
by infoinlet-marketplace

Persistent searchable memory for AI agents — save/get/search across sessions, tags.

28 installs/wk local only
Wet MCP
by n24q02m

Open-source MCP server for AI agents: web search, content extraction, and library docs.

3 069 installs/wk local only
Nan Forget
by nanmesh

AI that remembers. Local-first cross-session, cross-project long-term memory for coding tools.

74 installs/wk local only
Longmem
by marerem

Persistent cross-project memory for Cursor and Claude Code using local semantic search.

49 installs/wk local only
Goldhold
by jerrysrodz

Persistent memory for AI agents. Search, store, and recall across sessions.

30 installs/wk answering

Memory OS AI — questions

Answers built from our own checks of this server.

Why is there no uptime for Memory OS AI?
Memory OS AI 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 memory-os-ai was installed 58 times last week.
How do I connect Memory OS AI?
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 memory-os-ai straight from pypi; nothing to host, nothing to sign up for.
How many people use Memory OS AI?
The pypi package memory-os-ai was installed 58 times in the last week. Week over week that is -23%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Memory OS AI open source?
Yes — it is published under the GPL-3.0 licence, written in Python and 3 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.