Cognitive Memory
Persistent structured memory that compounds understanding across sessions instead of resetting it.
A Fleet domain · running on the frozen substrate
The problem it answers
Systems that forget between sessions can't accumulate understanding. Every conversation starts at zero.
Why it matters
Durable, structured memory is what turns repeated information into compounding knowledge.
6 Fleet Deployments
The deployments
Open on GitHub. Every system below runs on the same frozen decision substrate — this domain is one more proof that the substrate never needed editing.
orthos
experimentalA locally sovereign, replayable, graph-executed cognitive system.
Python
github.com/kliewerdaniel/orthos →divine-light
activeUnified AI memory system combining MemPalace verbatim storage, Graphify knowledge graphs, and Synt-inspired reasoning agents.
Python
github.com/kliewerdaniel/divine-light →sovereign-memory-bank
productionSeven-layer cognitive memory architecture for autonomous agents: raw documents → synthesized abstractions → cross-document insights.
Python · Ollama
github.com/kliewerdaniel/sovereignBank →brain-memory-graphrag-engine
activeUnified system that combines sovereign Graph RAG with self-improving agent memory.
Python
github.com/kliewerdaniel/Brain-Memory-GraphRAG-Engine →bot series
experimentalMultiple AI chatbot and research assistant iterations exploring GraphRAG, MCP integration, and conversational interfaces.
Python · Next.js
github.com/kliewerdaniel/bot001 →basicbot
experimentalSophisticated Research Assistant powered by GraphRAG technology for analyzing documents and research data.
Python · Next.js
github.com/kliewerdaniel/basicbot →