feat: resurrect Bezalel with Gemma 4 + llama.cpp stack

- Add EPIC.md with resurrection plan
- Create Hermes profile with Bezalel persona
- Add llama-server.sh for Gemma 4 inference
- Update start_bezalel.sh with stack checks
- Add README with quick start guide

Backend: llama.cpp
Model: Gemma 4 26B MoE (Apache 2.0)
Frontend: Hermes profile

No OpenAI. No cloud. Pure sovereign stack.

.gitconfig

@@ -1,5 +1,5 @@
 [user]
 	name = Allegro
-	email = allegro@timmy.local
+	email = allegro@timmytimmychen.com
 [credential]
 	helper = store