How do I install Cortexgraph Memory MCP Server?

Follow the setup instructions on the Cortexgraph Memory GitHub repository, then add the server configuration to your AI client.

What category is Cortexgraph Memory MCP Server?

Cortexgraph Memory is categorized under Knowledge & Memory. Browse more servers in these categories on MCPgee.

Cortexgraph Memory

Name: Cortexgraph MCP Server
Author: prefrontal-systems

v1.0.0•Knowledge & Memory•stable

Temporal memory system for AI assistants with human-like forgetting curves. All data stored locally in human-readable formats: JSONL for short-term memory, Markdown (Obsidian-compatible) for long-term. Memories naturally decay unless reinforced. Feat

aiai-assisstantclaudecognitive-sceincecognitive-science

Stars

Downloads

Weekly

0/5

View on GitHub

What is Cortexgraph Memory?

Cortexgraph Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to temporal memory system for ai assistants with human-like forgetting curves. all data stored locally in human-readable formats: jsonl for short-term memory, markdown (obsidian-compatible) for long-term...

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

Temporal memory system for AI assistants with human-like for

Use Cases

Temporal memory with forgetting curves

Human-readable memory formats

Obsidian integration

prefrontal-systems

Maintainer

LicenseAGPL-3.0

Languagehtml

Versionv1.0.0

UpdatedMay 6, 2026

Statushealthy

Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

View Source Browse All Servers

Installation

Manual Installation

npx cortexgraph

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms

ThroughputMedium

Resource Usage

Memory UsageLow

CPU UsageLow

How to Set Up and Use Cortexgraph Memory

CortexGraph is a Python-based MCP server that gives AI assistants like Claude a human-like memory system modeled on the Ebbinghaus forgetting curve. Memories stored through conversation naturally decay over time unless reinforced by repeated use, and frequently-accessed memories are promoted to permanent long-term storage as Obsidian-compatible Markdown files. Short-term memories are stored locally as human-readable JSONL files, giving users full control over their data without any cloud service dependency.

Prerequisites

Python 3.10+ runtime
uv, pipx, or pip for installation
An MCP-compatible client such as Claude Desktop
Optional: Obsidian installed for viewing and editing long-term memory Markdown files

Install CortexGraph from PyPI

Install using uv tool install for the best isolation. This installs the cortexgraph command and all 7 CLI utilities in an isolated environment.

uv tool install cortexgraph
# or with pipx
pipx install cortexgraph
# or with pip
pip install cortexgraph

Create the configuration directory and .env file

CortexGraph reads configuration from ~/.config/cortexgraph/.env. Create the directory and configure storage paths and decay parameters.

mkdir -p ~/.config/cortexgraph
curl -o ~/.config/cortexgraph/.env \
  https://raw.githubusercontent.com/prefrontal-systems/cortexgraph/main/.env.example

Edit the .env configuration file

Customize the storage path and decay model. The default 3-day power-law half-life is suitable for most users. Increase CORTEXGRAPH_PL_HALFLIFE_DAYS for longer retention.

# Storage location for short-term JSONL memories
CORTEXGRAPH_STORAGE_PATH=~/.config/cortexgraph/jsonl
# Decay model: power_law | exponential | two_component
CORTEXGRAPH_DECAY_MODEL=power_law
# Half-life in days (default: 3 days)
CORTEXGRAPH_PL_HALFLIFE_DAYS=3.0

Find the absolute path to the cortexgraph executable

Claude Desktop requires absolute paths to executables. Find the path using which and use it in the MCP config.

which cortexgraph
# Example output: /Users/yourname/.local/bin/cortexgraph

Configure Claude Desktop

Add CortexGraph to your Claude Desktop configuration at ~/Library/Application Support/Claude/claude_desktop_config.json using the absolute path from the previous step.

Restart Claude Desktop

Restart Claude Desktop to load the server. On first launch, CortexGraph creates the storage directory automatically.

Cortexgraph Memory Examples

Client configuration

Claude Desktop config block using the absolute path to the installed cortexgraph binary. Replace the path with the output of 'which cortexgraph' on your system.

{
  "mcpServers": {
    "cortexgraph": {
      "command": "/Users/yourname/.local/bin/cortexgraph"
    }
  }
}

Prompts to try

Example prompts that save, reinforce, and recall memories through natural conversation.

- "Remember that I prefer TypeScript over JavaScript for all new projects"
- "What are my coding preferences that you remember?"
- "I mentioned last week that I use dark mode — what else do you remember about my setup?"
- "Save this decision: we're using PostgreSQL instead of MySQL for the user database"
- "Show me my stored memories related to database choices"

Troubleshooting Cortexgraph Memory

Claude Desktop cannot find the cortexgraph executable

GUI apps like Claude Desktop do not inherit your shell PATH. Use the full absolute path returned by 'which cortexgraph' in the config. Common locations are /Users/yourname/.local/bin/cortexgraph (uv) or /Users/yourname/.local/pipx/envs/cortexgraph/bin/cortexgraph (pipx).

Memories are not persisting between conversations

Verify CORTEXGRAPH_STORAGE_PATH in your .env file points to a writable directory. Check that the .env file is at ~/.config/cortexgraph/.env. You can test storage by running 'cortexgraph --help' in the terminal and checking if the config directory exists.

Old memories are disappearing faster than expected

Increase CORTEXGRAPH_PL_HALFLIFE_DAYS in ~/.config/cortexgraph/.env (default is 3 days). For research or archival workflows, set it to 7-14 days. Memories are also promoted to permanent long-term storage once accessed 5+ times within 14 days.

Frequently Asked Questions about Cortexgraph Memory

What is Cortexgraph Memory?

Cortexgraph Memory is a Model Context Protocol (MCP) server that temporal memory system for ai assistants with human-like forgetting curves. all data stored locally in human-readable formats: jsonl for short-term memory, markdown (obsidian-compatible) for long-term. memories naturally decay unless reinforced. feat It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Cortexgraph Memory?

Follow the installation instructions on the Cortexgraph Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Cortexgraph Memory?

Cortexgraph Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Cortexgraph Memory free to use?

Yes, Cortexgraph Memory is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Cortexgraph Memory Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Cortexgraph Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & Memory Browse All Servers

Set Up Cortexgraph Memory in Your Editor

Choose your AI client for step-by-step setup instructions.

🖥️

Claude Desktop

macOS & Windows app

⌨️

Claude Code

CLI & terminal

📝

Cursor

AI-first code editor

💻

VS Code

GitHub Copilot MCP

🏄

Windsurf

Codeium AI editor

🔌

Cline

VS Code extension

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Cortexgraph Memory?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides

Explore All Servers Read Our Guides