Persistent Knowledge Graph Memory for AI Coding Agents. Adds long-term context (goals, strategies, preferences) to Cursor, Windsurf, & VS Code via MCP.

🧠 MCP-KG-Memory

The Long-Term Memory Layer for AI Coding Agents

Give your AI Assistant a brain that persists context, learns from past mistakes, and understands your project's goals.

Quick Start • Features • Installation • Configuration • License

📖 Overview

MCP-KG-Memory is a production-grade Model Context Protocol (MCP) Server designed to solve the "context amnesia" problem in AI coding assistants (Cursor, Windsurf, VS Code, Antigravity).

Instead of starting from zero every session, this system maintains a persistent Knowledge Graph of your project. It acts as an active memory layer that tracks:

• 🎯 Goals & Status: What are we building? What is done?
• 🛑 Constraints & Rules: Architectural decisions, forbidden patterns.
• 💡 Strategies & Outcomes: What worked? What failed? (Automatic learning)
• ❤️ User Preferences: How do you like your code written?
• 🔗 Code Relationships: Semantic links between goals and specific files.

📸 Visualization

Real-time visualization of the Knowledge Graph memory structure.

✨ Features

🧠 Active Context Injection (kg_autopilot)

Every time you start a task, the agent consults the memory. It automatically retrieves:

• Active goals relevant to your current work.
• Past failed attempts (to avoid repeating them) and successful strategies.
• Your specific coding preferences (SOLID, Clean Arch, etc.).

🔍 Semantic & Graph Search

Don't just grep strings. The system traverse