README
Wax is a Swift library providing a memory layer for on-device AI agents. It’s described as “The SQLite for AI memory. One file. Full RAG. Zero infrastructure.”
Created by Christopher Karani, Wax replaces complex RAG pipelines with a single portable file format, designed for privacy-first, offline-capable AI applications on Apple platforms.
Documents
| Document | Description |
|---|---|
| Architecture and Storage | Technical deep-dive into Wax’s custom binary format, SQLite FTS5 integration, HNSW vector indexing, and Metal GPU acceleration |
Related Research
- SQLite - Wax uses SQLite FTS5 for BM25 full-text search
- Vector Search - HNSW implementation via USearch library