docs: add links to WebGPU version and Twitter

README.md

@@ -23,3 +23,9 @@ The right-hand panel surfaces what the model actually produced:
 
 GGUF: [`AlexWortega/qwen35-4b-soyuz-merged-gguf`](https://huggingface.co/AlexWortega/qwen35-4b-soyuz-merged-gguf)
 (`Q4_K_M`, MTP head dropped — `--no-mtp` — since llama.cpp does not yet run Qwen3.5 MTP).
+
+---
+
+⚡ **WebGPU version** (runs fully in your browser): [`AlexWortega/pi-agent`](https://huggingface.co/spaces/AlexWortega/pi-agent)
+
+🐦 Follow me on Twitter/X: [@justALEXWORTEGA](https://x.com/justALEXWORTEGA)