init: Kira — AI body double with Honcho memory

Full voice pipeline (Whisper STT -> DeepSeek LLM -> OpenAI TTS),
animated SVG avatar (Live2D-ready), girly-pop UI, lofi music,
timer/notes/pets/wardrobe widgets, 10 background scenes with
particle effects, Honcho cross-session memory.

.env.example

@@ -0,0 +1,13 @@
+# ─── Kira Backend ───
+# OpenAI for STT (Whisper) and TTS
+OPENAI_API_KEY=sk-...
+# DeepSeek for LLM (personality/brain)
+DEEPSEEK_API_KEY=sk-...
+DEEPSEEK_MODEL=deepseek-chat
+
+# ─── Honcho Memory (optional) ───
+# Get API key at https://app.honcho.dev/api-keys
+# Uses production cloud by default. Set HONCHO_BASE_URL for local/self-hosted.
+HONCHO_API_KEY=hch-...
+DEEPSEEK_API_KEY=sk-your-deepseek-api-key-here
+DEEPSEEK_MODEL=deepseek-chat