Kartikk-26/Graphiti-MCP-Demo

This repo demonstrates Graphiti MCP integration with Cursor and Neo4j, storing AI prompts as real-time knowledge graphs for persistent memory.

25
/ 100
Experimental

This project helps AI developers and engineers give their AI agents a reliable, long-term memory. It takes natural language prompts and conversations from tools like Cursor or Claude, processes them, and stores the extracted context as structured knowledge graphs in a Neo4j database. The output is a persistent, queryable memory that helps AI agents understand past interactions and respond more contextually.

No commits in the last 6 months.

Use this if you are an AI developer or engineer building AI agents and need a robust, persistent memory system that can store and retrieve conversational context and structured data over time.

Not ideal if you are looking for a simple, in-memory conversational history for a single-turn chatbot or if you don't use AI agents or knowledge graph databases.

AI Agent Development Knowledge Graph Conversational AI Prompt Engineering Context Management
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 7 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Python

License

Last pushed

Sep 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/Kartikk-26/Graphiti-MCP-Demo"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.