ZenBrain memory as core
The full seven-layer architecture carries every conversation. Working memory for active tasks, episodic memory for history, procedural memory for learned routines.
Track C
„What does an AI platform look like that carries knowledge work — modular, with real memory, and reasoning steps organisations can inspect?"
ZenAI is the productive research application of the ZenBrain architecture. It shows that the memory research holds in practice — not only as a benchmark, but as a tool.
Motivation
The productive application is not a side-product of the fundamental research — it is the stress test. A memory architecture that only works on benchmarks has limited value. An architecture that carries knowledge work day-to-day proves itself on a different level.
ZenAI is therefore both: a productive AI operating system for knowledge work and the test vehicle for the ZenBrain research. What the papers describe runs here in productive use since the beginning of 2026.
Methodological approach
Three core decisions shape the platform. First, ZenAI is modular — each functional unit (memory, tools, vision, code execution) can be used independently or replaced. Second, real memory instead of simulated persistence — the full seven-layer memory architecture carries every conversation. Third, transparency — tool use, reasoning, and memory access are visible to the user.
This is complemented by a process-atlas methodology for AI adoption in organisations: a systematic mapping of existing processes prior to the AI implementation, combined with a three-year stepwise adoption framework.
Core components
The full seven-layer architecture carries every conversation. Working memory for active tasks, episodic memory for history, procedural memory for learned routines.
Code execution (Python, Node.js, Bash, sandboxed), vision API, web search, GitHub, calendar, email intelligence, maps — addressable modularly.
Systematic mapping of existing processes before AI implementation. In research — methods paper in preparation.
Stepwise adoption methodology for organisations — from the first pilot application to AI-augmented work throughout. In development.
Anthropic Claude (primary), Mistral (cloud fallback), Ollama (local inference). Researchers and authorities can choose the provider based on data-protection requirements.
The entire application layer can be fully self-hosted. LLM providers are configured separately; local inference is possible.
Get involved
Application studies with universities, pilot projects with research institutions, and methodological discussion on AI adoption in organisations are explicitly welcome.
research@zensation.aiMore from this research
Three tracks, one core, a shared ethics foundation.