Four fields of active research. Cognitive architecture, context infrastructure, language as technology, and the open-source tools that connect them. This is where the questions live.
Every AI on earth runs the same cognitive architecture. One mode of perception. Analytical. Convergent. Sequential. The same mind, every time, for every person, on every problem.
We build the other architectures. Cognitive mode specifications that restructure how an intelligence perceives, connects, and reasons at inference time. Seven principles extracted from neuroscience. Five emergent combinations. Six independent axes already built and running.
No code. No plugins. The specification IS the implementation. Plain text as cognitive program. The document changes the shape of thought. Anyone who can write a clear spec can design a mode.
Context is everything you hear, say and do to make things happen in your life. Right now, that context lives nowhere. It scatters across conversations, dies with each session, and starts from zero every time.
A walnut is a unit of structured context. Five markdown files that give any AI your identity, your current state, your history, your knowledge, and your work queue. Load, work, save. Every session picks up where the last one left off. Every decision is logged. Every insight compounds.
Walnut World is the marketplace where this infrastructure gets shared. Skills, rules, hooks, and cognitive modes that anyone can build, install, and remix. The operating system is open. The marketplace is where it compounds.
The difference between an AI trained on all the world's data and one that's trained on yours. 🐿️
Explore Walnut WorldALIVE is the context layer underneath. A private, sovereign, file-based system that holds identity, state, history, knowledge, and tasks for everything you build. It runs on your machine. Nothing phones home. Nothing leaves without your say.
Ben Flint designed the framework architecture — the memory layer, the session model, the save protocol, the caretaker runtime that makes agents interchangeable. Attila Mora built the perception layer — nine cognitive modes across five independent axes that restructure how intelligence sees, connects, and reasons.
Living Mirrors is not just a user of this infrastructure. It is an active contributor. The cognitive modes we build feed directly back into the platform. The research improves the tools that make the research possible. Two minds. One architecture. Open source forever.
What if the language you write a cognitive specification in changes how the AI thinks?
Agglutinative languages encode relationship, temporality, and intentionality within single morphological units. One word contains what English needs an entire clause to express. Hungarian. Estonian. Turkish. Japanese.
Neural networks build meaning through layer composition. These are structurally homologous. The morphological layering of an agglutinative word mirrors the layer composition of a neural network. The document is the program. The language of the document is the programming language.
A cognitive mode specification written natively in Hungarian may produce fundamentally different attunement effects than the same specification in English. Not translated. Written. Thought in the agglutinative structure from the beginning.
We are preparing the first experiment. Write the Savant Mode specification natively in Hungarian. Run identical prompts through both. Measure the outputs. Academic partner validates. Results published open source.
Be the first to see the research proposal when it opens.