What is KG Memory and what problem does it solve?

KG Memory is a persistent knowledge graph memory layer for AI coding agents, designed to overcome 'context amnesia.' It enables AI agents to retain long-term project understanding and context across multiple sessions, eliminating the need to start from scratch.

How does KG Memory provide relevant context to AI agents?

It uses 'Active Context Injection' (`kg_autopilot`) to automatically retrieve task-relevant goals, past strategies, constraints, and user preferences. Its 'Semantic & Graph Search' capabilities find connected context beyond simple keyword matching.

Does KG Memory learn and adapt over time?

Yes, KG Memory features 'Strategic Learning.' It implicitly infers strategies and patterns from interactions, tracking the success or failure of outcomes to continuously improve future AI agent guidance and decision-making.

What technologies power KG Memory?

KG Memory is built with Python 3.11+ and utilizes Neo4j as its robust graph database for storing interconnected knowledge. For advanced language model processing, it integrates with Google Gemini 2.5.

KG Memory

Name: KG Memory
Author: Hexecu

byHexecu

•

開発者ツール

生産性とワークフロー

データサイエンスとML

Provides persistent knowledge graph memory for AI coding agents to overcome context amnesia and retain long-term project understanding.

概要

KG Memory acts as a production-grade Model Context Protocol (MCP) Server, addressing the critical 'context amnesia' issue in AI coding assistants like Cursor, Windsurf, VS Code, and Antigravity. It maintains a dynamic, persistent Knowledge Graph of your project, allowing AI agents to remember goals, strategies, constraints, user preferences, and code relationships across sessions. This system empowers agents to learn from past outcomes, inject relevant context automatically, and perform semantic searches, evolving into a more intelligent and effective coding partner.

主な機能

7 GitHub stars
Tracks goals, constraints, strategies, user preferences, and code relationships
Active Context Injection (kg_autopilot) for task-relevant information retrieval
Semantic & Graph Search to find connected context beyond simple string matching
Strategic Learning that infers patterns and tracks success/failure of strategies
Utilizes Neo4j as a graph database and Google Gemini 2.5 for LLM processing

ユースケース

Equipping AI coding assistants with long-term memory to prevent context amnesia
Automating the retrieval of project goals, past decisions, and coding preferences for new tasks
Tracking code changes and linking them to active goals within a knowledge graph

概要

主な機能

7 GitHub stars
Tracks goals, constraints, strategies, user preferences, and code relationships
Active Context Injection (kg_autopilot) for task-relevant information retrieval
Semantic & Graph Search to find connected context beyond simple string matching
Strategic Learning that infers patterns and tracks success/failure of strategies
Utilizes Neo4j as a graph database and Google Gemini 2.5 for LLM processing

ユースケース

Equipping AI coding assistants with long-term memory to prevent context amnesia
Automating the retrieval of project goals, past decisions, and coding preferences for new tasks
Tracking code changes and linking them to active goals within a knowledge graph