In Memoria MCP Server

by pi22by7 Your server? Claim it

local only

In Memoria runs on your own machine — the client starts it, so there is no endpoint to ping. 125 installs a week from npm.

Persistent codebase intelligence that gives AI assistants memory across sessions

Installs per day peak 57 · avg 14 · +124% w/w

a month agotoday

125

Installs / week

npm · in-memoria

—

Stars

on GitHub

—

Last commit

no releases in 90 days

—

License

language unknown

Nothing serious here today

Today is the operative word: we check In Memoria 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 in-memoria -- npx -y in-memoria

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

{
  "mcpServers": {
    "in-memoria": {
      "command": "npx",
      "args": [
        "-y",
        "in-memoria"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.in-memoria]
command = "npx"
args = ["-y", "in-memoria"]

.cursor/mcp.json

{
  "mcpServers": {
    "in-memoria": {
      "command": "npx",
      "args": [
        "-y",
        "in-memoria"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "in-memoria": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "in-memoria"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: OPENAI_API_KEY (Optional OpenAI API key for embeddings (falls back to local transformers.js)).

Alternatives to In Memoria

same job, measured the same way

In Memoria

by pi22by7

Persistent codebase intelligence that gives AI assistants memory across sessions

local only

Token Savior

by mibayy

Structural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.

local only

Memoize — persistent agent memory

by harrisonford

Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.

answering

Memory Poisoning Scanner

by guardbee

Scans agent code for untrusted input poisoning persistent cross-session memory

338 installs/wk local only

Memory Poisoning Scanner

by 4hmetuyar

Scans agent code for untrusted input poisoning persistent cross-session memory

local only

Nucleus

by eidetic-works

Persistent memory for AI agents — shared .brain across Claude Code, Cursor & Codex

738 installs/wk 28 tools answering

Carrick

by carrick-tools

TypeScript codebase intelligence for AI agents and IDEs, across every service and repo.

answering

coldstart

by akashgoenka

Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.

60 installs/wk local only

In Memoria — questions

Answers built from our own checks of this server.

Why is there no uptime for In Memoria?

In Memoria 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 in-memoria was installed 125 times last week.

How do I connect In Memoria?

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 in-memoria straight from npm; nothing to host, nothing to sign up for.

How many people use In Memoria?

The npm package in-memoria was installed 125 times in the last week. Week over week that is +124%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.