Grafted Titans: I Built a Plug-and-Play Neural Memory for Open-Weight LLMs

Using only an Nvidia DGX Spark Blackwell for €4,400

I am splitting this research into two parts. This article is the non-technical overview.

For the engineers and scientists, the deep dive is coming next. In the coming days, I will open-source everything: the code, the model weights, and the full mathematical framework. I am taking a little extra time to ensure the technical documentation meets a rigorous scientific standard. Stay tuned.

Executive Summary: Grafted Neural Memory for Everyone

This research introduces “Grafted Titans,” a novel architecture that solves the critical inability of LLMs to learn continuously from user interactions without the crippling costs of traditional retraining. By “grafting“, I mean attaching a trainable memory module to a frozen model.

By “grafting” a dynamic Neural Memory module onto a frozen, open-source model (Qwen-2.5) via a lightweight cross-attention adapter, I have created a system that can instantly memorize and retrieve new information with 44.7% accuracy on complex tasks, a massive improvement ov…