# Graph-enabled RAG module **URL:** \ **Category:** Feature Requests\ **Created:** [August 11, 2025, 2:31am UTC](https://forum.cursor.com/t/graph-enabled-rag-module/128229 "2025-08-11T02:31:18Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![iTopher](https://avatars.discourse-cdn.com/v4/letter/i/8e8cbc/32.png) [@iTopher](https://forum.cursor.com/u/iTopher)\ **Post date:** [August 11, 2025, 2:31am UTC](https://forum.cursor.com/t/graph-enabled-rag-module/128229/1 "2025-08-11T02:31:18Z")
Cursor frequently ignores rules that I establish even if I remind it that the rule exists. My understanding is that is caused by context window limits (because you’re sending everything to an LLM for a response regardless of whether or not there is local knowledge in the repository that we are working from). I would prefer to see this implemented in a way that supports a local RAG module that we can seed with relevant knowledge. This would enable interactions directly with the RAG first (no LLM API key usage required) and present back to us a plan for how to implement what we are asking about by using LLMs, very likely reducing the number of context-consuming round-trips that we need to make to get to an acceptable plan. I do realize that I could try to implement this feature myself using an MCP server and rules (but again, rules are frequently ignored) that sits in front of my own RAG API, but I’d rather this be a native feature. Each project that we work on using Cursor could have it’s own set of knowledge inputs relevant to streamline development. I’d even be willing to pay an add-on fee for RAG database storage. ---
**Author:** ![iTopher](https://avatars.discourse-cdn.com/v4/letter/i/8e8cbc/32.png) [@iTopher](https://forum.cursor.com/u/iTopher)\ **Post date:** [August 11, 2025, 6:30am UTC](https://forum.cursor.com/t/graph-enabled-rag-module/128229/2 "2025-08-11T06:30:48Z")
An alternative to this would be to create an API spec that I need to implement to include as a sort of middleware to interface with my own Graph-Enabled RAG environment. Then give me a way to associate my end point with a project. Effectively, this would be like adding a RAG tool that I can use, but I’m the one who manages the RAG environment. ---
**Author:** ![LebedevIV](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/lebedeviv/32/70938_2.png) [@LebedevIV](https://forum.cursor.com/u/LebedevIV)\ **Post date:** [August 12, 2025, 4:07pm UTC](https://forum.cursor.com/t/graph-enabled-rag-module/128229/3 "2025-08-12T16:07:12Z")
I supported you, and I also asked at this forum a similar question earlier and even suggested a solution. If you like experiments, you can pay attention to the project of effective error correction: > **[GitHub - onestardao/WFGY: WFGY — Semantic Reasoning Engine for LLMs (MIT)...](https://github.com/onestardao/WFGY)** > > WFGY — Semantic Reasoning Engine for LLMs (MIT) (WanFaGuiYi / 萬法歸一) Fixes RAG/OCR drift, interpretation collapse, and “ghost matches” with symbolic overlays + logic patches. ⭐️ Star if you’re exploring semantic RAG or hallucination mitigation. and my experienced recent project of an active memory bank optimized for AI assistants (early alpha, but it works, and it’s very simple, it helps me > **[GitHub - LebedevIV/ProjectGraphAgent](https://github.com/LebedevIV/ProjectGraphAgent)** > > Внесите свой вклад в развитие LebedevIV/ProjectGraphAgent, создав аккаунт на GitHub. ---
**Author:** ![LebedevIV](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/lebedeviv/32/70938_2.png) [@LebedevIV](https://forum.cursor.com/u/LebedevIV)\ **Post date:** [August 15, 2025, 7:53pm UTC](https://forum.cursor.com/t/graph-enabled-rag-module/128229/4 "2025-08-15T19:53:34Z")
> **[GitHub - CodeBoarding/CodeBoarding: 🪄 Interactive Diagrams for Code](https://github.com/CodeBoarding/CodeBoarding)** > > 🪄 Interactive Diagrams for Code