CortexGraph: Temporal Memory for AI

A Model Context Protocol (MCP) server providing human-like memory dynamics for AI assistants. Memories naturally fade over time unless reinforced through use, mimicking the Ebbinghaus forgetting curve.

📖 New to this project? Start with the ELI5 Guide for a simple explanation of what this does and how to use it.

What is CortexGraph?

CortexGraph gives AI assistants like Claude a human-like memory system.

The Problem

When you chat with Claude, it forgets everything between conversations. You tell it "I prefer TypeScript" or "I'm allergic to peanuts," and three days later, you have to repeat yourself. This is frustrating and wastes time.

What CortexGraph Does

CortexGraph makes AI assistants remember things naturally, just like human memory:

• 🧠 Remembers what matters - Your preferences, decisions, and important facts

• ⏰ Forgets naturally - Old, unused information fades away over time (like the Ebbinghaus forgetting curve)

• 💪 Gets stronger with use - The more you reference something, the longer it's remembered

• 📦 Saves important things permanently - Frequently used memories get promoted to long-term storage

How It Works (Simple Version)

1. You talk naturally - "I prefer dark mode in all my apps"

2. Memory is saved automatically - No special commands needed

3. Time passes - Memory gradually fades if not used

4. You reference it again - "Make this app dark mode"

5. Memory gets stronger - Now it lasts even longer

6. Important memories promoted - Used 5+ times? Saved permanently to your Obsidian vault

No flashcards. No explicit review. Just natural conversation.

Why It's Different

Most memory systems are dumb:

• ❌ "Delete after 7 days" (doesn't care if you used it 100 times)

• ❌ "Keep last 100 items" (throws away important stuff just because it's old)

CortexGraph is smart:

• ✅ Combines recency (when?), frequency (how often?), and importance (how critical?)

• ✅ Memories fade naturally like human memory

• ✅ Frequently used memories stick around longer

• ✅ You can mark critical things to "never forget"

Related MCP server: AGI MCP Server

Technical Overview

This repository contains research, design, and a complete implementation of a short-term memory system that combines:

• Novel temporal decay algorithm based on cognitive science

• Reinforcement learning through usage patterns

• Two-layer architecture (STM + LTM) for working and permanent memory

• Smart prompting patterns for natural LLM integration

• Git-friendly storage with human-readable JSONL

• Knowledge graph with entities and relations

Why CortexGraph?

🔒 Privacy & Transparency

All data stored locally on your machine - no cloud services, no tracking, no data sharing.

• Short-term memory: Human-readable JSONL files (~/.config/cortexgraph/jsonl/)

  • One JSON object per line

  • Easy to inspect, version control, and backup

  • Git-friendly format for tracking changes

• Long-term memory: Markdown files optimized for Obsidian

  • YAML frontmatter with metadata

  • Wikilinks for connections

  • Permanent storage you control

You own your data. You can read it, edit it, delete it, or version control it - all without any special tools.

Core Algorithm

The temporal decay scoring function:

$$ \Large \text{score}(t) = (n_{\text{use}})^\beta \cdot e^{-\lambda \cdot \Delta t} \cdot s $$

Where:

• $\large n_{\text{use}}$ - Use count (number of accesses)

• $\large \beta$ (beta) - Sub-linear use count weighting (default: 0.6)

• $\large \lambda = \frac{\ln(2)}{t_{1/2}}$ (lambda) - Decay constant; set via half-life (default: 3-day)

• $\large \Delta t$ - Time since last access (seconds)

• $\large s$ - Strength parameter $\in [0, 2]$ (importance multiplier)

Thresholds:

• $\large \tau_{\text{forget}}$ (default 0.05) — if score < this, forget

• $\large \tau_{\text{promote}}$ (default 0.65) — if score ≥ this, promote (or if $\large n_{\text{use}}\ge5$ in 14 days)

Decay Models:

• Power‑Law (default): heavier tail; most human‑like retention

• Exponential: lighter tail; forgets sooner

• Two‑Component: fast early forgetting + heavier tail

See detailed parameter reference, model selection, and worked examples in docs/scoring_algorithm.md.

Tuning Cheat Sheet

• Balanced (default)

  • Half-life: 3 days (λ ≈ 2.67e-6)

  • β = 0.6, τ_forget = 0.05, τ_promote = 0.65, use_count≥5 in 14d

  • Strength: 1.0 (bump to 1.3–2.0 for critical)

• High‑velocity context (ephemeral notes, rapid switching)

  • Half-life: 12–24 hours (λ ≈ 1.60e-5 to 8.02e-6)

  • β = 0.8–0.9, τ_forget = 0.10–0.15, τ_promote = 0.70–0.75

• Long retention (research/archival)

  • Half-life: 7–14 days (λ ≈ 1.15e-6 to 5.73e-7)

  • β = 0.3–0.5, τ_forget = 0.02–0.05, τ_promote = 0.50–0.60

• Preference/decision heavy assistants

  • Half-life: 3–7 days; β = 0.6–0.8

  • Strength defaults: 1.3–1.5 for preferences; 1.8–2.0 for decisions

• Aggressive space control

  • Raise τ_forget to 0.08–0.12 and/or shorten half-life; schedule weekly GC

• Environment template

  • MNEMEX_DECAY_LAMBDA=2.673e-6, MNEMEX_DECAY_BETA=0.6

  • MNEMEX_FORGET_THRESHOLD=0.05, MNEMEX_PROMOTE_THRESHOLD=0.65

  • MNEMEX_PROMOTE_USE_COUNT=5, MNEMEX_PROMOTE_TIME_WINDOW=14

Decision thresholds:

• Forget: $\text{score} < 0.05$ → delete memory

• Promote: $\text{score} \geq 0.65$ OR $n_{\text{use}} \geq 5$ within 14 days → move to LTM

Key Innovations

1. Temporal Decay with Reinforcement

Unlike traditional caching (TTL, LRU), Mnemex scores memories continuously by combining recency (exponential decay), frequency (sub-linear use count), and importance (adjustable strength). See Core Algorithm for the mathematical formula. This creates memory dynamics that closely mimic human cognition.

2. Smart Prompting System

Patterns for making AI assistants use memory naturally:

Auto-Save

User: "I prefer TypeScript over JavaScript"
→ Automatically saved with tags: [preferences, typescript, programming]

Auto-Recall

User: "Can you help with another TypeScript project?"
→ Automatically retrieves preferences and conventions

Auto-Reinforce

User: "Yes, still using TypeScript"
→ Memory strength increased, decay slowed

No explicit memory commands needed - just natural conversation.

3. Natural Spaced Repetition

Inspired by how concepts naturally reinforce across different contexts (the "Maslow effect" - remembering Maslow's hierarchy better when it appears in history, economics, and sociology classes).

No flashcards. No explicit review sessions. Just natural conversation.

How it works:

1. Review Priority Calculation - Memories in the "danger zone" (0.15-0.35 decay score) get highest priority

2. Cross-Domain Detection - Detects when memories are used in different contexts (tag Jaccard similarity <30%)

3. Automatic Reinforcement - Memories strengthen naturally when used, especially across domains

4. Blended Search - Review candidates appear in 30% of search results (configurable)

Usage pattern:

User: "Can you help with authentication in my API?"
→ System searches, retrieves JWT preference memory
→ System uses memory to answer question
→ System calls observe_memory_usage with context tags [api, auth, backend]
→ Cross-domain usage detected (original tags: [security, jwt, preferences])
→ Memory automatically reinforced, strength boosted
→ Next search naturally surfaces memories needing review

Configuration:

MNEMEX_REVIEW_BLEND_RATIO=0.3           # 30% review candidates in search
MNEMEX_REVIEW_DANGER_ZONE_MIN=0.15      # Lower bound of danger zone
MNEMEX_REVIEW_DANGER_ZONE_MAX=0.35      # Upper bound of danger zone
MNEMEX_AUTO_REINFORCE=true              # Auto-reinforce on observe

See docs/prompts/ for LLM system prompt templates that enable natural memory usage.

4. Two-Layer Architecture

┌─────────────────────────────────────┐
│   Short-term memory                 │
│   - JSONL storage                   │
│   - Temporal decay                  │
│   - Hours to weeks retention        │
└──────────────┬──────────────────────┘
               │ Automatic promotion
               ↓
┌─────────────────────────────────────┐
│   LTM (Long-Term Memory)            │
│   - Markdown files (Obsidian)       │
│   - Permanent storage               │
│   - Git version control             │
└─────────────────────────────────────┘

Quick Start

Installation

Recommended: UV Tool Install (from PyPI)

# Install from PyPI (recommended - fast, isolated, includes all 7 CLI commands)
uv tool install cortexgraph

This installs cortexgraph and all 7 CLI commands in an isolated environment.

Alternative Installation Methods

# Using pipx (similar isolation to uv)
pipx install cortexgraph

# Using pip (traditional, installs in current environment)
pip install cortexgraph

# From GitHub (latest development version)
uv tool install git+https://github.com/simplemindedbot/cortexgraph.git

For Development (Editable Install)

# Clone and install in editable mode
git clone https://github.com/simplemindedbot/cortexgraph.git
cd cortexgraph
uv pip install -e ".[dev]"

Configuration

IMPORTANT: Configuration location depends on installation method:

Method 1: .env file (Works for all installation methods)

Create ~/.config/cortexgraph/.env:

# Create config directory
mkdir -p ~/.config/cortexgraph

# Option A: Copy from cloned repo
cp .env.example ~/.config/cortexgraph/.env

# Option B: Download directly
curl -o ~/.config/cortexgraph/.env https://raw.githubusercontent.com/simplemindedbot/cortexgraph/main/.env.example

Edit ~/.config/cortexgraph/.env with your settings:

# Storage
MNEMEX_STORAGE_PATH=~/.config/cortexgraph/jsonl

# Decay model (power_law | exponential | two_component)
MNEMEX_DECAY_MODEL=power_law

# Power-law parameters (default model)
MNEMEX_PL_ALPHA=1.1
MNEMEX_PL_HALFLIFE_DAYS=3.0

# Exponential (if selected)
# MNEMEX_DECAY_LAMBDA=2.673e-6  # 3-day half-life

# Two-component (if selected)
# MNEMEX_TC_LAMBDA_FAST=1.603e-5  # ~12h
# MNEMEX_TC_LAMBDA_SLOW=1.147e-6  # ~7d
# MNEMEX_TC_WEIGHT_FAST=0.7

# Common parameters
MNEMEX_DECAY_LAMBDA=2.673e-6
MNEMEX_DECAY_BETA=0.6

# Thresholds
MNEMEX_FORGET_THRESHOLD=0.05
MNEMEX_PROMOTE_THRESHOLD=0.65

# Long-term memory (optional)
LTM_VAULT_PATH=~/Documents/Obsidian/Vault

Method 2: Environment variables in Claude Desktop config

Add environment variables directly to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "cortexgraph": {
      "command": "cortexgraph",
      "env": {
        "MNEMEX_STORAGE_PATH": "~/.config/cortexgraph/jsonl",
        "MNEMEX_DECAY_MODEL": "power_law",
        "MNEMEX_PL_ALPHA": "1.1",
        "MNEMEX_PL_HALFLIFE_DAYS": "3.0",
        "LTM_VAULT_PATH": "~/Documents/Obsidian/Vault"
      }
    }
  }
}

Where cortexgraph looks for .env files:

1. Primary: ~/.config/cortexgraph/.env ← Use this for uv tool install / uvx

2. Fallback: ./.env (current directory) ← Only works for editable installs

MCP Configuration

Standard installation (uv tool install / pipx / pip):

{
  "mcpServers": {
    "cortexgraph": {
      "command": "cortexgraph"
    }
  }
}

Configuration loaded from ~/.config/cortexgraph/.env or environment variables (see Configuration section above).

For development (editable install):

{
  "mcpServers": {
    "cortexgraph": {
      "command": "uv",
      "args": ["--directory", "/path/to/cortexgraph", "run", "cortexgraph"],
      "env": {"PYTHONPATH": "/path/to/cortexgraph/src"}
    }
  }
}

Configuration can be loaded from ./.env in the project directory OR ~/.config/cortexgraph/.env.

Troubleshooting: Command Not Found

If Claude Desktop shows spawn cortexgraph ENOENT errors, the cortexgraph command isn't in Claude Desktop's PATH.

macOS/Linux: GUI apps don't inherit shell PATH

GUI applications on macOS and Linux don't see your shell's PATH configuration (.zshrc, .bashrc, etc.). Claude Desktop only searches:

• /usr/local/bin

• /opt/homebrew/bin (macOS)

• /usr/bin

• /bin

• /usr/sbin

• /sbin

If uv tool install placed cortexgraph in ~/.local/bin/ or another custom location, Claude Desktop can't find it.

Solution: Use absolute path

# Find where cortexgraph is installed
which cortexgraph
# Example output: /Users/username/.local/bin/cortexgraph

Update your Claude config with the absolute path:

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

Replace /Users/username/.local/bin/cortexgraph with your actual path from which cortexgraph.

Alternative: System-wide install

You can also install to a system location that Claude Desktop searches:

# Option 1: Link to /usr/local/bin
sudo ln -s ~/.local/bin/cortexgraph /usr/local/bin/cortexgraph

# Option 2: Install with pipx/uv to system location (requires admin)
sudo uv tool install git+https://github.com/simplemindedbot/cortexgraph.git

Maintenance

Use the maintenance CLI to inspect and compact JSONL storage:

# Show storage stats (active counts, file sizes, compaction hints)
cortexgraph-maintenance stats

# Compact JSONL (rewrite without tombstones/duplicates)
cortexgraph-maintenance compact

Migrating to UV Tool Install

If you're currently using an editable install (uv pip install -e .), you can switch to the simpler UV tool install:

# 1. Uninstall editable version
uv pip uninstall cortexgraph

# 2. Install as UV tool
uv tool install git+https://github.com/simplemindedbot/cortexgraph.git

# 3. Update Claude Desktop config to just:
#    {"command": "cortexgraph"}
#    Remove the --directory, run, and PYTHONPATH settings

Your data is safe! This only changes how the command is installed. Your memories in ~/.config/cortexgraph/ are untouched.

Migrating from STM Server

If you previously used this project as "STM Server", use the migration tool:

# Preview what will be migrated
cortexgraph-migrate --dry-run

# Migrate data files from ~/.stm/ to ~/.config/cortexgraph/
cortexgraph-migrate --data-only

# Also migrate .env file (rename STM_* variables to MNEMEX_*)
cortexgraph-migrate --migrate-env --env-path ./.env

The migration tool will:

• Copy JSONL files from ~/.stm/jsonl/ to ~/.config/cortexgraph/jsonl/

• Optionally rename environment variables (STM_* → MNEMEX_*)

• Create backups before making changes

• Provide clear next-step instructions

After migration, update your Claude Desktop config to use cortexgraph instead of stm.

CLI Commands

The server includes 7 command-line tools:

cortexgraph                  # Run MCP server
cortexgraph-migrate          # Migrate from old STM setup
cortexgraph-index-ltm        # Index Obsidian vault
cortexgraph-backup           # Git backup operations
cortexgraph-vault            # Vault markdown operations
cortexgraph-search           # Unified STM+LTM search
cortexgraph-maintenance      # JSONL storage stats and compaction

Visualization

Interactive graph visualization using PyVis:

# Install visualization dependencies
pip install "cortexgraph[visualization]"
# or with uv
uv pip install "cortexgraph[visualization]"

# Or install dependencies manually
pip install pyvis networkx

# Generate interactive HTML visualization
python scripts/visualize_graph.py

# Custom output location
python scripts/visualize_graph.py --output ~/Desktop/memory_graph.html

# Custom data paths
python scripts/visualize_graph.py --memories ~/data/memories.jsonl --relations ~/data/relations.jsonl

Features:

• Interactive network graph with pan/zoom

• Node colors by status (active=blue, promoted=green, archived=gray)

• Node size based on use count

• Edge colors by relation type

• Hover tooltips showing full content, tags, and entities

• Physics controls for layout adjustment

The visualization reads directly from your JSONL files and creates a standalone HTML file you can open in any browser.

MCP Tools

11 tools for AI assistants to manage memories:

Example: Unified Search

Search across STM and LTM with the CLI:

cortexgraph-search "typescript preferences" --tags preferences --limit 5 --verbose

Example: Reinforce (Touch) Memory

Boost a memory's recency/use count to slow decay:

{
  "memory_id": "mem-123",
  "boost_strength": true
}

Sample response:

{
  "success": true,
  "memory_id": "mem-123",
  "old_score": 0.41,
  "new_score": 0.78,
  "use_count": 5,
  "strength": 1.1
}

Example: Promote Memory

Suggest and promote high-value memories to the Obsidian vault.

Auto-detect (dry run):

{
  "auto_detect": true,
  "dry_run": true
}

Promote a specific memory:

{
  "memory_id": "mem-123",
  "dry_run": false,
  "target": "obsidian"
}

As an MCP tool (request body):

{
  "query": "typescript preferences",
  "tags": ["preferences"],
  "limit": 5,
  "verbose": true
}

Example: Consolidate Similar Memories

Find and merge duplicate or highly similar memories to reduce clutter:

Auto-detect candidates (preview):

{
  "auto_detect": true,
  "mode": "preview",
  "cohesion_threshold": 0.75
}

Apply consolidation to detected clusters:

{
  "auto_detect": true,
  "mode": "apply",
  "cohesion_threshold": 0.80
}

The tool will:

• Merge content intelligently (preserving unique information)

• Combine tags and entities (union)

• Calculate strength based on cluster cohesion

• Preserve earliest created_at and latest last_used timestamps

• Create tracking relations showing consolidation history

Mathematical Details

Decay Curves

For a memory with $n_{\text{use}}=1$, $s=1.0$, and $\lambda = 2.673 \times 10^{-6}$ (3-day half-life):

Use Count Impact

With $\beta = 0.6$ (sub-linear weighting):

Frequent access significantly extends retention.

Documentation

• Scoring Algorithm - Complete mathematical model with LaTeX formulas

• Smart Prompting - Patterns for natural LLM integration

• Architecture - System design and implementation

• API Reference - MCP tool documentation

• Bear Integration - Guide to using Bear app as an LTM store

• Graph Features - Knowledge graph usage

Use Cases

Personal Assistant (Balanced)

• 3-day half-life

• Remember preferences and decisions

• Auto-promote frequently referenced information

Development Environment (Aggressive)

• 1-day half-life

• Fast context switching

• Aggressive forgetting of old context

Research / Archival (Conservative)

• 14-day half-life

• Long retention

• Comprehensive knowledge preservation

License

MIT License - See LICENSE for details.

Clean-room implementation. No AGPL dependencies.

Knowledge & Memory

• mem0ai/mem0-mcp (Python) - A MCP server that provides a smart memory for AI to manage and reference past conversations, user preferences, and key details.

• cortexgraph (Python) - A Python-based MCP server that provides a human-like short-term working memory (JSONL) and long-term memory (Markdown) system for AI assistants. The core of the project is a temporal decay algorithm that causes memories to fade over time unless they are reinforced through use.

• modelcontextprotocol/server-memory (TypeScript) - A knowledge graph-based persistent memory system for AI.

Related Work

• Model Context Protocol - MCP specification

• Ebbinghaus Forgetting Curve - Cognitive science foundation

• Research inspired by: Memoripy, Titan MCP, MemoryBank

Citation

If you use this work in research, please cite:

@software{cortexgraph_2025,
  title = {Mnemex: Temporal Memory for AI},
  author = {simplemindedbot},
  year = {2025},
  url = {https://github.com/simplemindedbot/cortexgraph},
  version = {0.5.3}
}

Contributing

Contributions are welcome! See CONTRIBUTING.md for detailed instructions.

🚨 Help Needed: Windows & Linux Testers!

I develop on macOS and need help testing on Windows and Linux. If you have access to these platforms, please:

• Try the installation instructions

• Run the test suite

• Report what works and what doesn't

See the Help Needed section in CONTRIBUTING.md for details.

General Contributions

For all contributors, see CONTRIBUTING.md for:

• Platform-specific setup (Windows, Linux, macOS)

• Development workflow

• Testing guidelines

• Code style requirements

• Pull request process

Quick start:

1. Read CONTRIBUTING.md for platform-specific setup

2. Understand the Architecture docs

3. Review the Scoring Algorithm

4. Follow existing code patterns

5. Add tests for new features

6. Update documentation

Status

Version: 1.0.0 Status: Research implementation - functional but evolving

Phase 1 (Complete) ✅

• 10 MCP tools

• Temporal decay algorithm

• Knowledge graph

Phase 2 (Complete) ✅

• JSONL storage

• LTM index

• Git integration

• Smart prompting documentation

• Maintenance CLI

• Memory consolidation (algorithmic merging)

Future Work

• Spaced repetition optimization

• Adaptive decay parameters

• Performance benchmarks

• LLM-assisted consolidation (optional enhancement)

Built with Claude Code 🤖