JellyGo Family Drive Assistant

I'm Jelly, a college teacher. As a coding novice, winning at OpenAgents hackathon opened a new world for AI multi-agent scenario implementation. Thanks to organizers for this quality platform!

Targeting 'decision overload' and 'tedious execution' pain points in long-distance road trips, JellyGo! aims at multi-child families' self-driving 'energy pain points', liberating drivers from trip planning and range anxiety. Unlike fragmented experiences of checking guides while managing kids, JellyGo! achieves 'one sentence to customize entire package.' Through OpenAgents Network, system generates optimal routes based on any vehicle parameters (gas/electric/hybrid). Whether family outings or hardcore expeditions, it closes massive fragmented tasks, letting users focus on driving and scenery.

Multi-Agent collaboration network on OpenAgents framework: Main Agent (RoadTripMainAgent) coordinates requirements with trip planning, resource binding, vehicle adaptation functional Agents; supports any vehicle type via public info matching, achieving division of labor through preset instructions, quickly outputting full-process self-driving plans for family needs.

8 clearly divided AI Agents coordinated by Main Agent: Road Trip Main Agent (Commander): Core scheduling hub receiving fuzzy requirements, auto-decomposing tasks, ensuring solution consistency. Charlie (Info Collector): Precisely extracts key info like traveler count, vehicle type, time, budget, preferences. Budget-calculator (Accountant): Smart full-trip cost calculation including toll-free policies, 30% emergency reserve, visual budget table. Route-planner: Plans 'dynamic-static alternating' daily itinerary matching driving and touring rhythm. Charging-station (Energy Expert): Adapts to NEV characteristics, dynamically adjusts energy nodes by temperature/parameters. Critic (Safety Consultant): Child safety threshold model filtering high-risk items. Weather-agent: Precise meteorological data, warns extreme weather, adjusts itinerary.