Sub-Millisecond RAG on Apple Silicon. No Server. No API. One File

Wax

The SQLite for AI memory.

One file. Full RAG. Zero infrastructure.

Quick Start • Performance • How It Works • Install

30-Second Demo

import Wax // Create a memory file let brain = try await MemoryOrchestrator ( at : URL ( fileURLWithPath : " brain.mv2s " ) ) // Remember something try await brain . remember ( " User prefers dark mode and gets headaches from bright screens " , metadata : [ " source " : " onboarding " ] ) // Recall with RAG let context = try await brain . recall ( query : " user preferences " ) // → "User prefers dark mode and gets headaches from bright screens" // + relevant context, ranked and token-budgeted

That's it. No Docker. No vector DB. No network calls.

The Problem

You wanted to add memory to your AI app.

3 hours later you're still configuring Docker Compose for a vector database that crashes if you look at it wrong, sends your data to who-knows-where, and needs a DevOps team to keep running.

... continue reading