Wax

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

#ai-agents#cli#coreml#coreml-framework#data-science#machine-learning#mcp#mcp-server#memory#memory-cache#memory-hacking#metal#on-device-ai#rag#rag-pipeline#swift#vector-database#vector-embeddings#vector-search#vectordb

Install

git clone https://github.com/christopherkarani/Wax.git

Claude Desktop config

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "wax": {
      "command": "npx",
      "args": [
        "-y",
        "github:christopherkarani/Wax"
      ]
    }
  }
}

From the README

Wax is a high-performance, single-file memory layer for AI agents on Apple platforms. On-device, private, and portable. No server and no cloud dependency. English · Español · Français · 日本語 · 한국어 · Português · 中文 --------------|:-----------------------|:-----------------------|:-----------------------| | **Search** | Hybrid (Text + Vector) | Text Only* | Vector Only* | | **Latency** | **~6ms (p95)** | ~10ms (p95) | 150ms - 500ms+ | | **Privacy** | 100% Local | 100% Local | Cloud-hosted…

Read full README on GitHub →