1. What is MIMU? MIMU is a mobile/web-based intelligent medical assistant designed to detect pain sounds, verify that these sounds come from the owner of the phone, and automatically trigger emergency alerts when the patient cannot respond. It works entirely on-device, using the microphone, lightweight audio processing, and smart logic — ideal for elderly people, patients with chronic pain, or individuals living alone. 2. Core Features ✓ Pain Sound Detection Continuously listens for high-intensity sounds that may indicate distress or pain using RMS audio analysis. ✓ Owner Voice Verification Before triggering any emergency alert, the system checks whether the sound came from the registered owner using: MFCC features Additional spectral features Local similarity comparison (cosine distance) This dramatically reduces false alarms caused by other people or background noise. ✓ Emergency Alert Automation If a possible pain event occurs: The user gets a 10-second auto-cancel prompt. If they do NOT respond → the system automatically sends an alert to: Caregivers Emergency contacts Medical assistants A connected automation system (Make/EasyConnect webhook) ✓ Fully Local Processing All raw audio stays on the device. Only processed data (MFCC vectors + event info) is stored locally. ✓ Webhook Integration Easily connects with: Make / EasyConnect Telegram bots Airtable SMS or WhatsApp alert systems

Fotopico was created to solve a familiar problem: we all take thousands of photos but can rarely find the exact moment we’re looking for. Instead of scrolling endlessly, Fotopico uses AI to truly “understand” your images. Fotopico is an intelligent visual search platform that leverages Google’s Gemini Vision API and Qdrant vector embeddings to create a powerful semantic photo retrieval system. When users upload images, Fotopico automatically analyzes each one, extracting high-level features such as objects, scenes, context, text, and emotional cues. These embeddings are stored in a vector database optimized for similarity search. When a user enters a query, Fotopico converts the text into an embedding and performs a nearest-neighbor search to return ranked results with confidence scores. This enables natural language photo search—far beyond basic metadata or object detection. Fotopico solves the universal problem of disorganized photo libraries by offering fast, intelligent, and context-aware retrieval.

The AI-Powered Space Tutor simplifies access to space data for researchers, educators, and enthusiasts. Using Groq API, OpenAI models, NASA datasets, and Tavily search, it delivers AI-driven insights and real-time space exploration knowledge through an intuitive Streamlit UI. A RAG model ensures accurate, context-aware responses, while the FastAPI backend enables seamless interaction. This project democratizes space education, making complex data more accessible and engaging. Technologies Used: Python, FastAPI, Streamlit Tavily Langchain LangGraph Unicorn Groq API (Llama 3), OpenAI (GPT-4o) NASA API, Tavily Search API Local & cloud deployment

Smart Meeting Summarizer Smart Meeting Summarizer revolutionizes how professionals manage meetings by transforming lengthy transcripts into actionable insights. It leverages cutting-edge AI technology, including NLP models, Gradio for a user-friendly interface, and Hugging Face Spaces for deployment, to deliver a seamless, interactive experience. The tool supports diverse input formats such as text, PDFs, and live transcriptions, making it versatile for various use cases. By summarizing key points, decisions, and action items, it helps users save time and stay focused on critical tasks. Additional features include keyword highlighting and sentiment analysis to provide context and enhance understanding. The backend, developed in Python, uses advanced libraries like Hugging Face's Transformers, spaCy, and NLTK to ensure high-quality processing. Gradio powers the intuitive frontend, allowing users to upload data, view summaries, and download insights effortlessly. Key benefits include: Time-saving: Quickly extract critical information from lengthy discussions. User-friendly: Clean interface for easy navigation. Action-oriented: Focus on decisions and next steps. Customizable: Supports multiple formats for diverse needs. Deployed on Hugging Face Spaces, Smart Meeting Summarizer ensures scalability, accessibility, and robust integration. Future plans include real-time summarization, multilingual support, and integrations with platforms like Slack and Zoom. Smart Meeting Summarizer is a powerful tool for professionals seeking efficiency and clarity in their meetings, turning conversations into actionable outcomes.

Tourism Industry is one of the major industry affecting revenue and impacting the lives of majority of population that resides in LATAM regions, we are building a super app that helps to tackle various issues and challenges. Navigating safety routes for tourists, helping local businesses with visibility, integrating art, culture, hidden gems and history for tourists to see and be aware of, helping with multi-lingual support, enabling user interactions, bookings and accommodations, enabling better replies from AI chatbot interactions and maintaining data about health and hygiene, balancing ecological factors while promoting Tourism are of key essence to this platform!

Join our $1,000,000+ startup challenge series powered by Surge ⏱️ 8 days to turn your idea, or existing product, into an investable demo. 📅 February 6 - 15, 2026 • Feb 6 - 14 (Online Phase) - Collaborate and build online with developers and AI innovators from around the world. All projects must be submitted by the end of the online phase on February 14th. • Feb 14 (On‑site Build Day) - Selected participants will be invited to an exclusive in‑person session to refine their projects and connect directly with mentors. • Feb 15 (On‑site Demos & Awards) - Live pitching sessions to a panel of judges and ecosystem partners, followed by the official winner announcement. 🌟 Get feedback from startup mentors and technical experts. 📍 On-site Venue (Feb 14–15): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 🤝 Join solo or with a team. New founders and existing startups are welcome. 🏆 $1,000,000+ in credits, token prizes, perks and funding opportunity. 📍 On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Apply now to build, validate, and pitch with purpose.

🔧 Spend 10 days launching your startup! 🚀 Improve your prototype previously developed at hackathons. 🤜 Collaborate with peers or work independently throughout the Hackathon. 🤖 Gain complimentary access to learning resources about Generative AI models, AI Agents, and beyond. 🚀 Explore opportunities with GAIA Startup Accelerator for Hackathon victors. 🌍 Connect and innovate alongside a worldwide AI community!

Create noteworthy apps with advanced reasoning across audio, vision, and text in real time with GPT-4o. 🕒 72 hours to complete the challenge 💡 Create revolutionary apps which use GPT-4o advanced features 🤝 Take part alone or form a team with other participants 🚀 Engage in a 3-day virtual development marathon and network with tech and business leaders 🏆 Win opportunity to participate in LabLab NEXT acceleration program

It’s a great opportunity to: 🚀 Leverage Google’s advanced Gemma 2 models to create cutting-edge solutions. 💰 Access resources to support your project development. 🌟 Receive guidance from expert mentors throughout the hackathon. 🤝 Work solo or in teams to bring your ideas to life. 🏆 Compete for a chance to choose from unique Google swag and enjoy an opportunity to meet the Gemma team for the best solutions! 🧑🏻‍💻 Sign up before the Kick-Off Stream to secure your spot! 🗓️ On-site Workshops: Join us in-person at Google Cloud Space in London on 28th November from 5:00 PM to 9:00 PM UK time (GMT) for hands-on workshops