The e-commerce platform (https://ecommerce-lyart-five-31.vercel.app/) is a sophisticated web application designed to deliver a seamless and innovative shopping experience. Developed using Next.js for server-side rendering, React for dynamic UI, and Tailwind CSS for responsive styling, it is backed by a Neon PostgreSQL database for robust data management. The platform integrates Groq AI to power advanced features, including: Voice Search: Users can search products using voice input, processed via Groq’s Whisper model to extract keywords (e.g., "laptop" from "search for laptops"), with a 4MB file size limit for audio uploads. Image Search: Allows product searches by uploading images, enhancing accessibility. Product Filters: Enables users to refine searches by category, price, and rating. Smart Filters: AI-driven filtering for personalized results based on user behavior. Responsive Design: Ensures compatibility across devices, from mobile to desktop.

DeepAgro is an AI-powered agricultural platform that transforms traditional farming with real-time crop health monitoring, pest and disease detection, climate adaptation strategies, and market insights. By leveraging AI-driven analytics, it helps farmers optimize resources, prevent losses, and increase productivity. DeepAgro offers image-based crop diagnosis, allowing farmers to detect diseases, nutrient deficiencies, and soil health issues instantly. With multilingual support and voice/image input, it ensures accessibility for all farmers. The platform provides automated alerts for extreme weather, pest outbreaks, and disease risks, enabling proactive decision-making.To address climate change impacts, DeepAgro integrates real-time climate intelligence, offering recommendations on planting schedules, irrigation, and fertilization. It also provides market-driven insights, helping farmers select profitable crops, find the best selling locations, and access government subsidies. For small-scale farmers facing resource constraints, DeepAgro generates personalized farming plans based on land, water, soil quality, and budget. Additionally, interactive visual reports, heatmaps, and predictive analytics help farmers assess risks and forecast yields effectively. By bridging the gap between traditional farming and modern AI technology, DeepAgro ensures higher yields, reduced losses, and sustainable agriculture, empowering farmers with smart, data-driven decision-making for a profitable and climate-resilient future.

"EduNexus 2.0" is an AI-powered educational platform that integrates IBM Watson Assistant's conversational AI with personalized learning tools to create an adaptive, intelligent learning environment. The platform offers a tailored experience to meet individual student needs. Powered by IBM Watson Granite Model , it provides real-time, context-aware support, utilizing natural language processing (NLP) to offer precise assistance for complex academic queries. Key features include a Personalized Learning Assistant that Customizes learning plans, an AI Coding Mentor for expert coding support, and a Smart Document Summarizer that simplifies complex content. The Interactive Study Planner helps students create personalized study schedules, while Real-Time Q&A offers instant academic support. Mental Health Support ensures students maintain well-being, and Multi-Language Support breaks down language barriers. EduNexus 2.0 also generates AI Study Resources, such as personalized materials and practice tests, along with Lecture Summaries that condense lengthy lectures for easier review. By combining IBM Watson’s conversational intelligence with adaptive learning algorithms, EduNexus 2.0 creates an intuitive, responsive ecosystem that enhances academic and technical skill development, supports mental wellness, and optimizes learning outcomes for students.

Government websites serve as sources of information and services related to public affairs, playing an essential role in connecting citizens with government institutions, but they are notorious for their complexity and lack of user-friendly design. The vast amount of information available on these sites can make it incredibly difficult to find what you're looking for. We created GovEase to make navigating government websites easier for users. All the user has to do to use GovEase is choose a language, choose a country, and input the government service or benefit they are looking for. The system will then find the documents and information that are responsive to the user's inquiry. GovEase can be used by native English speakers and people with limited English proficiency who speak Spanish, Hindi, French, Urdu, or German, because the results can be translated into one of these languages. GovEase searches any country's government websites to find government documents and information with ease. The tech stack we used for our project is Llama 3.2 (LLM), Browserless, Groq, Streamlit, Python, and LangDetect. Browserless does a search on Google based on the user's query. The search finds the top websites and gets the document links which is then given to LLama 3.2 which structuralizes the search results (output and links). LangDetect is a library that detects the language that the user wants and translates the results into the language the user wants. We are using Llama 3.2 from the Groq API key as the hosting platform and the front end deployment is hosted by Streamlit.

Pulse & Prism fully automates the creation of high-quality, short-form video content, designed specifically for platforms like TikTok and YouTube Shorts. Targeting the growing demand for visually engaging, accessible content, our tool transforms a simple theme or idea from the user into a complete, polished video in just a few steps. The process begins by generating a concise, impactful poem based on the user’s input using the Aria model. This poem captures the essence of the theme, providing a unique and creative textual foundation. Next, we use AI-driven text-to-speech (TTS) to convert the poem into a natural-sounding audio narration that enhances the mood and style of the content. Our tool then generates AI-crafted video clips that visually align with the poem, capturing its tone and essence through dynamic imagery. Finally, our system seamlessly combines the audio and video segments into a cohesive, shareable video that requires no additional editing from the user. While our MVP focuses on generating and assembling these videos, our future vision includes direct upload capabilities to social media platforms, scheduling tools, and analytics to provide users with seamless engagement insights. By transforming an idea into a ready-to-share video in minutes, our solution empowers creators of all experience levels to produce consistent, captivating content with minimal time and effort.

TeleGuide is an advanced AI assistant specifically designed for the telecommunications industry. Built on cutting-edge AI models like Llama 3.2, TeleGuide helps users efficiently handle various telecom-related tasks. Whether it’s analyzing regulatory documents, contracts, or customer inquiries, the app delivers detailed insights and actionable data. TeleGuide goes beyond text-based queries by offering image analysis as well. Users can upload satellite imagery or equipment photos for inspection and get a comprehensive analysis, all integrated with TelecomAI for enhanced accuracy and speed. With TeleGuide, telecom professionals have a versatile tool to streamline their work, making data processing and interpretation more efficient than ever.

Period Care is a holistic health platform designed to support individuals throughout their entire menstrual cycle, not just during their period. Our app offers personalized health insights, food recommendations, and emotional well-being tips tailored to each phase of the cycle. Users can track their periods, mood swings, and sleep patterns, helping them better understand their bodies. Additionally, the app provides easy access to nearby stores for purchasing pills or pads and allows users to book appointments with gynecologists. By focusing on both menstrual and non-menstrual phases, Period Care empowers users to take control of their health and well-being year-round.

Today’s litigators are expected to quickly make well-informed decisions and develop strong strategies and a big-picture perspective. To accomplish these goals in shorter time frames, we present Legal Buddy to streamline the document review and analysis process. Legal Buddy gives attorneys more time for strategic planning by providing a report with an overview of the case, a liability analysis, a case analysis, applicable laws and defenses, damages, and recommendations for the case. The attorney (user) can upload medical records or summaries, witness statements, deposition transcripts or summaries, pleadings, and other legal documents, notes, or summaries and the system will use Upstage's Document OCR to extract text from the documents. Then, the Llama model summarizes all the text and the text is given to the OpenAI's o1 LLM to generate a liability analysis and report. Additionally, we stored a data set of U.S. case law on MongoDB using LlamaIndex and enabled a vector search to find the relevant cases for the case analysis feature. The system matches information from our specific case from the uploaded documents with other cases from the data set of U.S. case law. OpenAI's o1 reasoning is used to generate case analysis and the case analysis is included in the report. There is currently a resource limit on the length of the documents that can be uploaded and the amount of cases that can be stored, so for now we are uploading summaries of legal documents instead of the actual documents and the data set we are storing is a sub-set (about 500 cases) of the entire U.S. case law data set. We would like to have more processing and storage functionality, but that just wasn't feasible for this hackathon. For the future, we would like the user to interact with live data from a data source (i.e. Westlaw, LexisNexis) instead of a data set. We would also like the user to query case information through a chat interface.

"DataVue" is a groundbreaking data science platform that aims to transform how we learn, understand, and apply data science. Developed by Team Synaptic Synergy , this revolutionary ecosystem seamlessly integrates cutting-edge AI technology with intuitive design to democratize data science education and empower the next generation of data professionals. Key features of DataVue include: 1. AI-Powered EDA: An intelligent analysis engine that uncovers hidden patterns in data. 2. Dynamic Visualizations: Tools to transform raw data into compelling visual stories. 3. 24/7 AI Assistant: A personal data science mentor available round-the-clock. 4. Smart Data Cleaning: AI-driven tools for effortless data preparation. 5. Adaptive Learning Paths: Personalized courses that evolve with users' skills. 6. Real-time Collaboration: Seamless teamwork capabilities for data projects. 7. Enterprise-Grade Security: Ensuring top-notch data safety. DataVue is designed to cater to a wide range of users, from beginners to experienced data scientists. The platform emphasizes community-driven development and welcomes contributions from developers, data enthusiasts, and innovators.

In this hybrid hackathon powered by Arc, developers will build the next generation of agentic commerce systems using Arc with USDC. Explore a world where AI agents and web services can pay for APIs, data, compute, and content in dynamic, usage-based ways, while Arc provides stablecoin-native settlement with predictable USDC fees and deterministic, sub-second finality. This hackathon is supported by Google & Google DeepMind, with a dedicated challenge and $10,000 in Google Cloud Platform (GCP) credits awarded for the best use of Gemini models and Google AI Studio. 📅 January 9 – 24, 2026 • Jan 9 – 23 (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 January 23rd. • Jan 23 (On‑site Build Day – San Francisco, CA) – Selected participants will be invited to an exclusive in‑person session to refine their projects and connect directly with mentors. • Jan 24 (On‑site Demos & Awards – San Francisco, CA) – Live pitching sessions to a panel of judges and ecosystem partners, followed by the official winner announcement. Get guidance from Arc and Circle experts through on-site support. 📍 On-site Venue (Jan 23–24): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 🤝 Go solo or team up, it's your flow. 🏆Compete for $10,000 in USDC & $10,000 in GCP Credits. 📍 On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑🏻‍💻 Secure your spot now - sign up before the Kick-Off Stream!

Explore Innovations in Language Processing and Image Generation! 🕒 72 hours to complete the challenge 💡 Create revolutionary tourism and culture apps 🤝 Take part alone or form a team with other participants 🚀 The final project can be used for your portfolio, and the startup application to the Slingshot accelerator 🏆 Win cash prizes, cloud credits, incubation & collaboration opportunities to develop your project further!

⌚ Dive into a 48-hour journey of creativity. 🚀 Compete to craft an app supercharged by Llama 3. 🎓 Expert mentors will guide you every step of the way. 🏆 Win an opportunity to participate in the Lablab NEXT acceleration program, exciting cash prizes, credits, and gear from LlamaIndex, Together AI & Zilliz 🧑🏻‍💻 Sign up before the Kick-Off Stream to secure your spot!

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