Back to browse
GitHub Repository

Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No Server. No API. One File. Pure Swift

757 starsSwift

Wax – RAG in a single file (SQLite for AI memory)

by karc14·Feb 13, 2026·2 points·0 comments

AI Analysis

●●SolidWizardryNiche Gem
The Take

Exports a one-file 'brain' and a tiny MemoryOrchestrator API (remember/recall) so you can ditch Docker and hosted vector DBs — token-budgeted, deterministic recall and kill-9-safe durability are concrete wins. The Metal-accelerated vector search plus SQLite FTS5 fallback shows real engineering heft, but it's clearly tuned for the Apple ecosystem and the author is still asking for retrieval/eval feedback.

Category
Target Audience

iOS/macOS app developers and mobile/edge AI engineers building on-device agents or apps that need private, offline RAG-style memory

Post Description

Wax is a Swift-native, on-device memory layer for agents: store documents + embeddings + hybrid retrieval in a single crash-safe file.

Goal: replace the typical “RAG stack” with something you can ship inside an app (offline, deterministic token budgeting, reproducible retrieval).

Feedback welcome — especially on retrieval quality + eval methodology.

Similar Projects

AI/ML●●●Banger

Mneme – Open-protocol AI memory that lives on your device

Beats Mem0 on strict keyword matching by preserving source language instead of paraphrasing.

Big BrainZero to One
ptengelmann
2022d ago