A multi-agent system for completing real-world tasks using Google Gemini 2.5 Flash.
- Medicine Finder: Find nearby pharmacies and simulate calls to check stock
- Bali Itinerary Planner: Create personalized travel itineraries with iterative updates
- Generative UI: Dynamic component rendering based on task context
- Task Registry: Easily extensible architecture for adding new tasks
cd server
npm install
cp .env.example .env
# Add your GEMINI_API_KEY to .env
npm run devcd client
npm install
npm run dev- Start the backend server (port 5000)
- Start the frontend dev server (port 3000)
- Open http://localhost:3000
- Try:
- "Find me ibuprofen 200mg near downtown"
- "Plan a 5-day Bali trip with $2000 budget"
- "Change day 2" (after creating an itinerary)
- Orchestrator: Manages task flow and agent coordination
- Planner Agent: Breaks down user intent into steps
- Retrieval Agent: Simulates data fetching
- Executor Agent: Generates outcomes
- UI Agent: Determines which components to render