An independent research lab in Kiel, Germany. We research collective intelligence on cognitive architecture — humans and machines together, on a structure that retains knowledge.

Every number on this page is backed by a public record, a passing test suite, or a reproducible build. Nothing here asks to be believed.

• In a controlled, same-budget benchmark judged by independent LLM judges, ZenBrain wins all nine answer-quality head-to-head comparisons (3 competitors × 3 judges) against Letta, Mem0 and A-Mem — and the paper also prints where it loses: retrieval-proper metrics to a competing system, an aggregate-F1 metric to lexical search.
• The memory library is extracted from a production platform (440K+ LOC, 12,000+ tests) — not a research toy. Building it from source yields the exact 153-file @zensation/algorithms@0.4.2 tarball published on npm.
• The research trail is fully public: 24 open records with DOIs, an arXiv preprint, and defensive publications establishing prior art.

7 layers, FSRS spaced repetition, Hebbian learning, emotional tagging, sleep consolidation. Pure TypeScript, zero dependencies, 528 tests.

npm install @zensation/algorithms

• Try it in your browser — runs the published code, no install.
• Packages: @zensation/algorithms · @zensation/core · @zensation/adapter-postgres · @zensation/adapter-sqlite · @zensation/cli
• Drop it into what you already use: @zensation/mcp gives any Model Context Protocol client the seven layers as four tools; @zensation/ai-sdk is Vercel AI SDK middleware that recalls before the model call and stores the turn after it.
• New here? Pick a good first issue or ask in Discussions.

The self-hosted AI OS ZenBrain was extracted from: 60 AI tools, multi-agent system, knowledge graph, real-time voice. Published as a frozen, readable snapshot (8 May 2026); it ships the @zensation/cli terminal agent.

• Preprint: arXiv:2604.23878 — ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems
• Corpus: 24 open records on Zenodo — nineteen preprints and five software / reproduction packages, every preprint under CC BY 4.0, each with its own version and concept DOI
• Author ID: ORCID 0009-0001-1793-012X
• Prior art: defensive publications on Technical Disclosure Commons
• Benchmarks are reported with the protocol, the effect sizes and the cases where the system loses — including the metric on which a competing system wins.

• Library questions → GitHub Discussions
• Research, replication, consortium inquiries → research@zensation.ai
• Everything else → open-source@zensation.ai · zensation.ai

Company: ZenSation Enterprise Solutions · Kiel, Germany · Code: Apache 2.0 · Records: CC BY 4.0 / Apache 2.0