Travigo

Source: Dev.to

Overview

Travigo is a next‑generation AI Agent that utilizes multimodal inputs and outputs, moving far beyond simple text‑in/text‑out interactions. It leverages Google’s Gen AI SDK, Gemini Live API, Gemini 3, and Google Maps API cloud services, combining generative AI with spatial context to solve complex problems and create immersive 3D navigation and storytelling experiences.

Features

Multimodal Interactions

• Communicate via voice and text while the AI processes real‑time visual context from interactive Street View and 3D map spatial data.

Dynamic Personas

• Concierge Mode: Realistic local guides.
• Game Mode: Mystical/run‑time personas.
• Additional local personas are generated on the fly by Gemini 3 based on the user’s AR location and street view.

Real‑time Context Processing

• Uses a Live Agent Orchestrator to stream dialogue and voice directly tied to user actions and spatial events.

Immersive Storytelling

• Generates contextual narratives that are overlaid seamlessly onto the UI and 3D environment.

Architecture

The project employs a multi‑model architecture, selecting different Gemini models from the Google Gen AI SDK depending on the task:

• Live Agent Orchestrator: Handles real‑time, multimodal conversations via voice and audio streaming.
• Scout Queries: Grounds location searches using the Google Maps tool.
• Strategic Analysis: Performs deep reasoning tasks such as planning logistics, tours, generating fictional personas based on spatial context, and conducting visa planning or historic deep dives, all grounded by Google Search.

Gemini Models Used