SmartMemory MCP Server

by smartmemory Your server? Claim it

local only

SmartMemory runs on your own machine — the client starts it, so there is no endpoint to ping. 934 installs a week from pypi.

Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.

Installs per day peak 1 286 · avg 304 · +44% w/w

a month agotoday

934

Installs / week

pypi · smartmemory-mcp

—

Stars

on GitHub

—

Last commit

from GitHub

—

License

language unknown

Nothing serious here today

Today is the operative word: we check SmartMemory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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 smartmemory-mcp -- uvx smartmemory-mcp

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

{
  "mcpServers": {
    "smartmemory-mcp": {
      "command": "uvx",
      "args": [
        "smartmemory-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.smartmemory-mcp]
command = "uvx"
args = ["smartmemory-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "smartmemory-mcp": {
      "command": "uvx",
      "args": [
        "smartmemory-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "smartmemory-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "smartmemory-mcp"
      ]
    }
  }
}

Alternatives to SmartMemory

same job, measured the same way

Memtomem

by memtomem

Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.

2 691 installs/wk local only

Keymem

by donggyun112

Associative key-graph memory for LLM agents — recall by association, not vector similarity.

662 installs/wk local only

Memory Kernel

by artem362

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

118 installs/wk local only

sqlite-graph-memory

by tonydzi

Recall over your markdown notes: vector search plus your [[wikilinks]] as a graph, in SQLite.

752 installs/wk local only

Memwright

by bolnet

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

146 installs/wk local only

Continuum

by pouyahasanamreji

Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.

local only

RemembrallMCP

by cdnsteve

Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.

29 installs/wk local only

Hindsight MemPalace

by holetron

Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector

8 installs/wk local only

SmartMemory — questions

Answers built from our own checks of this server.

Why is there no uptime for SmartMemory?

SmartMemory 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 smartmemory-mcp was installed 934 times last week.

How do I connect SmartMemory?

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 smartmemory-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use SmartMemory?

The pypi package smartmemory-mcp was installed 934 times in the last week. Week over week that is +44%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.