on-device-ai

I built Wax, a single-file crash-safe memory engine for AI agents on Apple Silicon: WAL durability, hybrid RAG, bitemporal facts, no cloud dependency.

I built Swarm's Swift web tool for 4,096-token on-device LLMs. Here's the tiered envelope, the Wax-without-embeddings bet, and fourteen decisions behind it.

A 3B on-device model with a 4K context window produced a 2,336-word grounded research report using live web search. Here's the architecture that made it work.