Skip to content
Prompt

cortexgraph — System Prompt

by prefrontal-systems

AI Summary

CortexGraph is a temporal memory system for AI assistants that implements human-like forgetting curves using local storage (JSONL and Markdown), enabling natural conversation memory across Claude, Cursor, and other platforms without explicit save commands.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to add the "cortexgraph — System Prompt" prompt rules to my project.
Repository: https://github.com/prefrontal-systems/cortexgraph

Please read the repo to find the rules/prompt file, then:
1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type)
2. If there's an existing rules file, merge the new rules in rather than overwriting
3. Confirm what was added

Description

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. Features knowledge graphs, smart prompting, and MCP server integration for Claude.

Overview

CortexGraph’s true power lies not in its MCP tools alone, but in how LLMs are taught to use them naturally. This document describes the smart prompt interpretation system — patterns and techniques for making AI assistants remember things like humans do, without explicit commands.

Smart Prompt Interpretation for Memory Systems

Version: 0.2.0 Last Updated: 2025-01-07

Core Principle

> Memory operations should be invisible to the user. When you tell a friend "I prefer tea over coffee," they remember without saying "OK, I'm saving that to my memory database." CortexGraph enables AI assistants to do the same through carefully designed system prompts.

1. Auto-Save (Capture Important Information)

When to trigger: • User shares preferences or personal information • User makes decisions or plans • User provides corrections or feedback • User shares factual information about themselves or their projects • User establishes conventions or workflows Examples: ` User: "I prefer using TypeScript over JavaScript for all new projects" → Auto-save to STM with tags: ["preferences", "typescript", "programming"] User: "The database password is in /home/user/.env" → Auto-save to STM with tags: ["credentials", "database", "security"] • High strength=1.5 for security-critical info User: "I've decided to go with the monorepo approach" → Auto-save to STM with tags: ["decisions", "architecture", "monorepo"] ` Implementation Pattern: `python

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 1mo ago
Active
AdoptionUnder 100 stars
27 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Stars27
Forks6
Issues3
Updated1mo ago
View on GitHub
AGPL-3.0 License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Any AI assistant that accepts custom rules or system prompts

Claude
ChatGPT
Cursor
Windsurf
Copilot
+ more