Travel-Seek is an Agentic AI travel planner powered by Agno & Groq (DeepSeek). Orchestrates live web search tools to generate hyper-personalized, actionable itineraries in seconds.
# Travel-Seek Travel-Seek is an AI-powered travel planning assistant that helps you create personalized travel itineraries and answer travel-related questions. The application leverages a coordinated multi-agent team (powered by Agno + Groq) and optionally enriches results with real Google Places & Directions data via a custom MCP server plus verified OpenWeather forecasts. ## Features - **Multi-Agent Travel Planning**: Four specialized AI agents (Research, Itinerary, Budget, Local Expert) coordinate to produce comprehensive travel plans. - **Google Places Integration**: Real ratings, reviews, hours, and directions via a custom MCP server backed by the Google Maps API. - **OpenWeather Integration**: Verified current conditions and 5-day forecasts, with explicit long-range limitations instead of fabricated weather detail. - **Conversational Planning**: Chat naturally to build and refine your plan with session memory. - **Graceful Fallback**: Works without a Google Maps key — falls back to DuckDuckGo search with a visible warning. - **Standalone MCP Server**: The Places MCP server works independently with Claude Desktop or any MCP-compatible client. ## Installation ### 1. Clone the Repository ```sh git clone https://github.com/Mukku27/Travel-Seek.git cd Travel-Seek ``` ### 2. Create and Activate a Virtual Environment ```sh python3 -m venv .venv source .venv/bin/activate # On Windows use `.venv\Scripts\activate` ``` ### 3. Install Dependencies ```sh pip install -r requirements.txt ``` ### 4. Set Up Environment Variables Create a `.env` file in the root directory: ```sh GROQ_API_KEY='your_groq_api_key' GOOGLE_MAPS_API_KEY='your_google_maps_api_key' # Optional — enables Places & Directions OPENWEATHERMAP_API_KEY='your_openweather_api_key' # Optional — enables verified weather tools SERPI_API_KEY='your_serpi_api_key' # Optional: enable Tavily search alongside SerpAPI/DuckDuckGo USE_TAVILY='true' TAVILY_API_KEY='your_tavily_api_key' ``` The `GOOGLE_MAPS_API_KE
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型