The identity layer
Six things make your agents your agents.
Hicortex keeps all of them.
The LLM is a swappable engine — any model, any provider, today's or next year's. Hicortex is the layer around it that preserves everything from day to day, regardless of the model or the context window. One part you write; the rest is distilled automatically from real sessions, every night — and injected whenever any of your agents starts. The more agents you run, the more experience flows into the pool — and every one of them gets sharper.
The name is the architecture. In the human brain, the cortex is the layer wrapped around the core — it's where memory, personality, and judgment live. Hicortex is that layer for your agents.
Each agent keeps its own identity — its personality is its own. What all your agents share is the experience around you: who you are, your preferences, how you work, your values, your projects, your decisions, your corrections. Many agents, one life to remember.
Who the agent is: tone, rules, working style, its name if it has one. And it doesn't stay static — the agent reflects on its own experience and proposes refinements to who it is; you approve them. The same way people have matured for millennia: self-reflection, not reprogramming. You stay in control; it keeps becoming more itself.
self-reflecting · you approve changes · injected every session · never decays
Durable facts the agent holds: your stack, your projects, your constraints, the things that stay true beyond any single task.
distilled nightly · unused fades, relevant surfaces · every prompt, zero LLM calls
What actually happened: the tasks, the incidents, what worked and what failed — the agent's own history, searchable and pushed back when relevant.
distilled nightly · unused fades, relevant surfaces · every prompt, zero LLM calls
What was chosen and why. When a newer decision replaces an older one, the old one is marked superseded — the agent stops offering you April after July settled it.
distilled nightly · supersession-tracked · surfaced every prompt, zero LLM calls
Principles distilled from experience. Correct the agent once and it becomes a reusable learning — surfaced to every agent you run, wherever it applies.
nightly reflection · shared across agents
Who the agent knows: you, your preferences, the other agents it works alongside — the working relationship that otherwise resets to zero.
curated + derived from shared memory
