A reversible memory idea for long-running AI agents
A personal AI agent runs all day on a home server, using and cloud models while saving daily work notes as markdown files. The first idea was to give each project a unique value like a color, mix the day’s work into one blended color, and later read which projects were inside it. That fails because a color only has three numbers, which cannot carry enough information about roughly 50 projects and their shares.
The better model is closer to a chef tasting a dish, naming the ingredients, estimating their amounts, and noticing when something unfamiliar is present. The method uses older math called and vector symbolic s. Each project name creates the same 4,096-dimensional ±1 vector every time, and random high-dimensional vectors almost do not overlap.
A day’s work can then be stored as a weighted sum of project vectors and later broken back apart with dot products. Unlike embedding search, which mainly finds similar text, this memory layer aims to recover the structure of mixed work across projects.
Key points
- A personal AI agent keeps daily markdown logs of ongoing work.
- A simple color-like ID cannot store enough information to separate about 50 mixed projects later.
- represents each project with a large vector that is nearly separate from others.
- Dot products can help estimate which project vectors were part of a day’s mixed work.
- The goal is different from embedding search: it tries to unpack mixed project activity, not just find similar text.