Hi everyone,
I've been hacking on a local personal memory system called Hillock. Honestly, it's very much a work in progress and it isn't some flawless breakthrough, but I wanted to see if we could build a lightweight, completely offline memory layer for local LLMs without the overhead of running a heavy neural vector database or wasting precious VRAM.
The project is named after the biological Axon Hillock—the exact gatekeeper region of a human neuron that sums up incoming electrical charges and decides whether to fire (open the gate) or remain silent (block).
I wrote a tough, 30-sentence scientific benchmark with complex sentence structures and hard negatives (like asking what Einstein discovered when the text only mentions Curie discovering radioactivity and Einstein working with her).
Running Qwen 1.5B locally on my computer, here is how it actually did:
Why are these scores low? Because a tiny 1.5B model completely trips over complex English grammar during ingestion (it gets confused and creates weird predicates). However, the actual HDC vector-matching itself is incredibly stable. I enforce a Constant-Component-Count of exactly 3 components per fact, which balances the vector norms and keeps retrieval highly reliable once the facts are actually in the database.
It is fully open-source (under the AGPL-3.0 copyleft license) and designed to run entirely offline on consumer hardware.
If anyone is interested in VSAs, neuro-symbolic AI, or has feedback on the HDC context-binding math, I'd love for you to check it out!
**GitHub Repository:** [https://github.com/roandejager/Hillock](https://github.com/roandejager/Hillock)