Pinned Loading

1. Wax Wax Public

   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

   Swift 667 28

2. Swarm Swarm Public

   🐦‍🔥 A Lightweight Agent Orchestration Framework written in pure Swift 6.2

   Swift 394 25

3. Espresso Espresso Public

   Train and run transformers directly on Apple's Neural Engine — 4.76x faster than CoreML.

   Swift 79 4

4. Conduit Conduit Public

   🦑 Unified Swift SDK for LLM inference across local and cloud providers

   Swift 72 5

5. Terra Terra Public

   OpenTelemetry-native observability for on-device GenAI workloads

   Swift 8

6. EdgeRunner EdgeRunner Public

   🚀 LLM inference in Swift/Metal, Load GGUF, no conversion, no cpp, pure swift

   Swift 6