Travel Guide Network

An indie developer in the moment and long-term tech explorer. My work is a weather-based travel guide system that generates Hogwarts-style diverse travel suggestions based on weather, hoping it becomes a simple travel companion making trips more fun.

This project builds a multi-agent travel guide system based on OpenAgents framework. Core innovation lies in using YAML configuration to define different role instructions, enabling multiple Agents to concurrently process the same real-time weather data, generating differentiated personalized suggestions. The system achieves loosely-coupled collaboration and stable data flow control through Python script lightweight orchestration, combined with Ollama local models and strict source_id verification mechanism, completing complex workflow construction without writing underlying business logic.

System uses Python combined with YAML configuration for orchestration. Data entry builds Weather Connector HTTP service based on WorkerAgent, triggered by travel_sender script. Model calls use Ollama local service. For data flow, Connector publishes weather data in JSON format, multiple downstream Agents receive concurrently, strictly filtering message sources through source_id verification to ensure response only to specific instructions, effectively preventing infinite loops in multi-Agent environments.

Real-time weather data fetching: Automatically gets weather info based on input city and date. Automated instruction triggering: Supports one-click initialization of network layer and Agent processes via command line scripts. Multi-agent concurrent processing: Supports 5+ Agent nodes processing same input data simultaneously. Differentiated suggestion generation: Based on different System Instructions (like different Hogwarts house styles), outputs customized guides including outfits, activities and precautions. System stability guarantee: Prevents message confusion and loops in multi-Agent environments through source ID verification mechanism.