# TigerSheriff (Guest is God)

- **Event:** [Hospitality 2030: A Rosewood Sand Hill Hackathon](https://cerebralvalley.ai/e/rosewood-hospitality-2030)
- **When:** Sat, May 16 at 9:00 AM – 10:00 PM (PDT)
- **Where:** Rosewood Sand Hill, Menlo Park, CA
- **Team:** [P Kumar](https://cerebralvalley.ai/u/pkmr), [AKRAM SHERIFF](https://cerebralvalley.ai/u/akram-AI)
- **GitHub:** https://github.com/akramIOT/agentic-hospitality-concierge
- **Demo video:** https://www.youtube.com/watch?v=ApoIBk9Y-WU
- **Gallery:** https://cerebralvalley.ai/e/rosewood-hospitality-2030/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/rosewood-hospitality-2030/hackathon/gallery/33

An agentic AI hospitality concierge for Rosewood Sand Hill, Menlo Park and the global Rosewood portfolio. Guests get personalized, voice-first guidance booking, reservation in their native language—weather, dining, FX, card perks, trip planning, spa and dining bookings, and geofenced arrival—through a custom Python agent runtime (no third-party agent framework) with ElevenLabs voice and optional edge-tts fallback.

Short-term and long-term agentic memory are used extensively end to end: every lobby concierge turn carries session context forward, while returning guests get prior preferences and trip notes recalled across visits—then written back after each briefing for the next stay.

Runs fully on your laptop by default: Ollama LLM, local JSON storage, DuckDuckGo search. Set DEPLOYMENT_MODE=azure for Azure OpenAI + Cosmos DB when you need cloud scale.

---

Markdown version of https://cerebralvalley.ai/e/rosewood-hospitality-2030/hackathon/gallery/33. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt