restructure: proper project layout, README, kill training

- cuda/ — main LBM kernel (khra_gixx_1024_v5.cu)
- navigator/ — lattice_observer, golden_weave, bridges, mock daemon
- scripts/ — compile, start, launch, setup (paths updated)
- docs/ — system manual
- archive/ — everything else (old kernels, inquiries, experiments)
- README.md — full setup guide: requirements, quick start, use your own LLM
- removed training/ entirely (broken LoRA scripts + datasets)
- .gitignore: exclude build/ logs/ training/ *.jsonl

archive/misc/ollama_msg.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+curl -s http://localhost:11434/api/chat -d '{
+  "model": "lbm-embodied",
+  "messages": [{"role": "user", "content": "Continue the journey into the heart of the lattice."}],
+  "stream": false
+}' 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(r['message']['content'])"