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 738 46

2. Swarm Swarm Public

   Type-safe AI agents and multi-agent workflows for Swift

   Swift 483 38

3. Espresso Espresso Public

   Train and run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely

   Swift 111 5

4. Conduit Conduit Public

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

   Swift 102 12

5. EdgeRunner EdgeRunner Public

   🚀 LLM inference Engine in Swift/Metal, Load GGUF and safe tensors modes, no conversion, no cpp, pure swift

   Swift 35 1

6. ContextCore ContextCore Public

   ContextCore: The ultra-fast Metal context engine for on-device AI. Build optimized context windows in <5ms with perfect recall on Apple Silicon. 🧠⚡️🚀

   Swift 25 3