Add EdgeRunner to AI category

Fast, local LLM inference for Apple Silicon built in Swift/Metal.
Supports GGUF models (Qwen3, etc.) with Metal-optimized kernels
and ~230+ tok/s decode on M3 Max.

Author: christopherkarani

contents.json

@@ -1061,6 +1061,20 @@
       "description":"Compile transformers directly for Apple's Neural Engine.",
       "homepage":"https://github.com/christopherkarani/Espresso"
     },
+    {
+      "title":"EdgeRunner",
+      "category":"ai",
+      "description":"Fast, local LLM inference for Apple Silicon. Built in Swift and Metal from the ground up.",
+      "homepage":"https://github.com/christopherkarani/EdgeRunner",
+      "tags":[
+        "llm",
+        "inference",
+        "metal",
+        "gguf",
+        "apple-silicon",
+        "on-device-ai"
+      ]
+    },
     {
       "title":"CenteredCollectionView",
       "category":"uicollectionview",