Machine Learning

Local-First Memory (Mempalace / OpenViking bridge)

A dual-layer, fully local memory system that gives the AI stack persistent context without sending anything to the cloud. It combines spatial memory (vector storage with ChromaDB) with an execution-time RAG filesystem (viking://) organized into tiers.

A dual-layer, fully local memory system that gives the AI stack persistent context without sending anything to the cloud. It combines spatial memory (vector storage with ChromaDB) with an execution-time RAG filesystem (viking://) organized into tiers.
ChromaDB RAG RLM Python
Full Overview View Source

Related Projects

Machine Learning

Cross-Machine OCR Escalation

Machine Learning

Graph-Based Agent Memory (Honcho)

Machine Learning

Handwriting Recognition Pipeline