Hi, I'm Daniel from Zep. I've integrated the Cursor IDE with Graphiti, our open-source temporal knowledge graph framework, to provide Cursor with persistent memory across sessions. The goal was simple: help Cursor remember your coding preferences, standards, and project specs, so you don't have to constantly remind it.<p>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.<p>Key points of how this works:<p>- Custom entities like 'Requirement', 'Preference', and 'Procedure' precisely capture coding standards and project specs.<p>- Real-time updates let Cursor adapt instantly—if you change frameworks or update standards, the memory updates immediately.<p>- Persistent retrieval ensures Cursor always recalls your latest preferences and project decisions, across new agent sessions, projects, and even after restarting the IDE.<p>I’d love your feedback—particularly on the approach and how it fits your workflow.<p>Here's a detailed write-up: <a href="https://www.getzep.com/blog/cursor-adding-memory-with-graphiti-mcp/">https://www.getzep.com/blog/cursor-adding-memory-with-graphi...</a><p>GitHub Repo: <a href="https://github.com/getzep/graphiti" rel="nofollow">https://github.com/getzep/graphiti</a><p>-Daniel
What's the advantage over the built-in solution? (and before it, .cursorrules)<p><a href="https://docs.cursor.com/context/rules-for-ai" rel="nofollow">https://docs.cursor.com/context/rules-for-ai</a>
The over engineering here is commendable for something that provides most likely marginal value whilst still needing more api calls to summarize everything you do.
This looks interesting but somewhat complicated or not obvious how to get going in a classic "Show HN" style.<p>The requirement for an OpenAI key may also be a little off-putting, or at least, could do with some indication of realistic costs; most Cursor users will likely need a significant motivation to add to the subscription they already have.<p>Don't get me wrong, this could be a really worthwhile addition to the LLM coding toolset but I think it needs some work on the presentation as to how to get quickly up and running.
The concept is promising, but I tested it and found the performance quite poor. I used one of my Python projects for the test, which consists of about 10k lines of Python code. The model I utilized was Claude 3.7 Sonnet with thinking.<p>in the first conversation round, I asked Claude to grasp the overall project and initialize its memory. Unfortunately, Claude experienced a hallucination and generated an episode that included a full name entirely unrelated to my project's actual full name, as my project name is an abbreviation.<p>In the second conversation round, I provided Claude with the full name of my project and requested it to correct its memory. In response, Claude apologized and claimed that it now understood the full name of my project, but it did not utilize any MCP command.<p>In the third conversation round, I specifically asked it to use the MCP command to update its memory. Claude successfully added a new episode but failed to remove the incorrect old episode.<p>It wasn't until the fourth conversation round that I directly pointed out that it should eliminate the incorrect old episode, and Claude finally completed the memory initialization that should have been accomplished at the end of the first round.<p>I have set up the correct Cursor Rules according to the README.<p>At this point, it appears this project is challenging to use with natural language. I need to explicitly instruct Claude on which specific tools to call for various operations to achieve the intended outcome.<p>Am I doing something wrong?
not obvious to me why this is an improvement of having the agent just update the rule files directly itself; i have it do that to my various AI-targeted readme files and it works great.
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?
I don’t see how this is palatable by serious organizations? So you build this huge memory graph of preferences? But none of it is explicit? It’s all just magic? The attack vectors from a security angle seem insane. Also the absence of any explicitness in how you define standards seems completely not viable in a commercial context? I mean it’s crazy cool as a hobby project, but also seems not to have a serious commercial viability?
This is exciting!<p>Glancing through the article, I can't tell, is this Cursor specific? Some of us are raw dogging VS Code with <a href="https://cline.bot" rel="nofollow">https://cline.bot</a>, which supports MCP servers: <a href="https://cline.bot/mcp-marketplace" rel="nofollow">https://cline.bot/mcp-marketplace</a>.<p>Would love to try this out in Cline!
Looks super interesting. I hadn't heard of Graphiti before, but the idea of giving Cursor some kind of persistent, structured memory across sessions definitely sounds useful.
It's there some way to control what gets updated in the database and how and when?<p>For example I'd like to be in control of the archtectural patterns and not let the LLM drive this.