After 6 months of daily building, I just released Hillock v1.0 stable: a local neuro-symbolic memory engine that runs under 1.2GB VRAM with zero hallucinations
If you self-host local AI tools, you probably know how annoying it is to set up a memory layer. Most modern setups expect you to spin up multiple heavy Docker containers running dedicated vector databases that hog gigabytes of RAM just to store a couple of text documents.