One of the big problems I have with cursor is that it ignores the rules frequently. For example, working in the front-end it will sometimes totally ignore all the components that I have explicitly told it to use. Would this... fix that?
replies(2):
Before this integration, Cursor (an AI-assisted IDE many of us already use daily) lacked a robust way to persist user context. To solve this, I used Graphiti’s Model Context Protocol (MCP) server, which allows structured data exchange between the IDE and Graphiti's temporal knowledge graph.
Key points of how this works:
- Custom entities like 'Requirement', 'Preference', and 'Procedure' precisely capture coding standards and project specs.
- Real-time updates let Cursor adapt instantly—if you change frameworks or update standards, the memory updates immediately.
- Persistent retrieval ensures Cursor always recalls your latest preferences and project decisions, across new agent sessions, projects, and even after restarting the IDE.
I’d love your feedback—particularly on the approach and how it fits your workflow.
Here's a detailed write-up: https://www.getzep.com/blog/cursor-adding-memory-with-graphi...
GitHub Repo: https://github.com/getzep/graphiti
-Daniel
Using file pattern matching and automatic attachment makes it much, much more sticky in my experience.