LLM Wiki Memory
Agentic memory for AI apps — facts, events, and semantic recall
Platform-agnostic TypeScript engine for hybrid LLM memory. Episodic fact extraction, vector search, ontology graphs, and multi-agent architectures over SQLite. Bring your own adapter.
npm Packages
Platform-agnostic
SQLiteAdapter interface, zero runtime deps — bring your own adapter.
Semantic search
Embeddings + cosine similarity; MiniSearch keyword fallback.
Immutable vs mutable facts
Document-sourced vs inferred vs user-stated memory types.
Maintenance jobs
Librarian, heal, reembed, and prune background jobs.
Per-entity seeded ontology
Strict, Emergent, or Off modes for structured knowledge.
OKF v0.1 import/export
Open Knowledge Format interoperability for memory portability.
Production-proven in Clanker
Powers persistent memory in the Clanker AI companion app.
Tiered AI memory architecture
Inspired by Andrej Karpathy's LLM Wiki memory spec.
Powers persistent memory in Clanker— our personal AI companion with real-time voice.