Discover Best Apps according to The Community!

Discover the most voted AI applications that have been built during lablab.ai hackathons. Explore our AI Hackathon projects and get inspired to create your own!

CodeBaseBuddy

Tool Name: CodeBaseBuddy with Codestral Key Features: - Privacy-preserving: Locally deployable, ensuring all operations remain on the user's machine. - Semantic Code Search: Utilizes advanced techniques for precise and relevant code search results. - Accelerated Onboarding: Quickly brings new contributors up to speed with any codebase. - Error Reduction: Provides specific guidance to minimize mistakes and prevent bugs. - Enhanced Engagement: Encourages contributions from those hesitant due to unfamiliarity with the codebase. - Continuous Learning: Helps both newcomers and experienced developers discover and learn about lesser-known parts of the codebase. - Technical Implementation: - **Vector Indexing**: Builds an annoy vector index by generating embeddings for every file in the repository. - **Query Processing**: Utilizes Annoy for efficient querying of the vector index. - **Guidance Generation**: Leverages locally deployed Codestral to provide step-by-step instructions based on user queries. - Original Contributions: - Local LLMs for Semantic Code Search: Uses Ollama's local large language models for running and managing models on a user's laptop. - Advantages:: - Privacy: Everything is deployed locally, ensuring user data remains secure. - Speed: Accelerates the process of getting acquainted with a new codebase. - Accuracy: Reduces the likelihood of errors with precise guidance. - Encouragement: Motivates more community contributions by simplifying the onboarding process. - Learning: Continues to be a resource for experienced developers to explore and understand different parts of the codebase. Summary: CodeBaseBuddy with Codestral is a cutting-edge tool designed to streamline the onboarding process for new developers, provide precise code search capabilities, and enhance overall engagement and learning within development teams. By maintaining a local deployment, it ensures privacy while offering robust and innovative features.

CodeBaseBuddy
medal
LangChain

Sight beyond Sight

Our website enhances online content accessibility for the visually impaired with a cost-effective text-to-speech service using contemporary AI tools. Current market solutions lack necessary amenities and are costly. Working on the website: > once the website loads, the user inputs the URL of the website to be analyzed > this website is parsed using Beautiful Soup to gather the meaningful text content available on the page > this content is passed to the OpenAI text-davinci-003 model as a prompt and a summary is generated for the same > this summary is read out to the user using Azure in natural human tone > next, the website is again parsed using Beautiful Soup with the aim to download relevant images on that website > these images are then analyzed using Google Cloud Vision API and feature labels describing the prominent objects/contents of that image are generated > these labels are passed as a prompt to the OpenAI text-davinci-003 model and a meaningful sentence is generated which describes the images > the prompt already includes a set of sample labels and outputs that the model can use to understand the format of the desired output. > the image description generated in the above step is then read aloud using Azure. For Redis: Redis caches URL results for up to 3 hours, if URL exists in cache, output is displayed/read aloud. Otherwise, website is processed for new output. Results are removed after 3 hours for possible content changes. It allows for fast data access making it suitable for high performance use cases. For voice control: > using space bar, user can ask queries regarding summary through available chatbot > above query is converted to text via speech recognition library of python > this text and the summary are given to the OpenAI text-davinci-003 model as a prompt and the query is resolved > the result is spoken out and if speech unrecognized, an error message stating to retry is read aloud

Galacticos
RedisGPT-3

BiteBuddy Meal Planner

BiteBuddy is a meal-planning tool that is prized for its customization. What this entails is that for every different user, a different meal plan is generated based on the user's preferences, needs, and dislikes. A tool to create a meal plan needs to understand what the customer needs. Therefore, the tool asks the user about their body characteristics to help organize the facts needed to create a balanced diet. Precisely, the user's Body Mass Index (BMI) is calculated to give an idea about the possible goals and hence, display an adequate diet. After that, the tool asks the user about any allergies, if any exist, so as not to include these foods in the plan. Moreover, they are asked to input any preferences they might have to include in their diet. The user input is then processed to generate the data. After which, the data is sent via the APIs through properly formatted prompts. The generated meal plan is then displayed in table format for every day of the week and at least three meals per day. Each meal has its nutritional values displayed, including carbohydrates, calories, fats, and proteins; the tool also suggests the right portions and the recipe with the ingredients that aid in preparing that meal. The recipe sub-window also illustrates the meal by providing a photo. Sorting is a feature that can be used to sort the meals based on their nutritional facts. The main advantage of this website is that it groups everything that the user might need to plan a healthy diet, considering their allergies and any food preferences they might have for the week. The tool replaces the need to visit nutritionists and explore different food regimes. It also replaces searching and exploring various recipes among multiple cooking platforms.

The DeCoders
ChatGPTDALL-E-2GPT-3

Autonomous Agents from APIs - Zero Code Builder

Using Vultr, Groq, Llama, Coral, and Fetch.ai, our project introduces a transformative way to generate and deploy Autonomous AI Agents from APIs—a no-code, prompt-driven AI Agent Builder and conversational interface to manage intelligent agents across enterprise systems in real time. From Prompt ➜ Plan ➜ Code ➜ Execute ➜ Iterate ➜ Deploy ➜ Use (on Coral, Custom, and Fetch AI) User explains their goal in natural language. Our AI locates relevant APIs, generates step-by-step agent plans, writes the code, deploys tools to Vultr-hosted MCP servers, and registers them with Coral and Fetch.ai. All agents are accessed via a multi-modal chat interface—text or voice—enabling users to test, refine, and operate agents live. These agents interact with real-world APIs via the MCP servers created through the Agent Builder. No code. Just intent. From developers and marketers to support and operations teams—anyone can turn apps into automations, tools, or digital workers. Enterprise-ready and built for the future of work, Vortex IQ enables users to go from idea to working agent in minutes. All AI inference runs on Groq’s ultra-low-latency hardware using Llama 3 models, making it fast, private, and cost-efficient. Agents are also composable via Fetch.ai’s Agentverse and ASI:One. Future-Ready with Scalable Impact: a. 3,000+ Retailers: Rolling out AI agents across BigCommerce, Adobe Commerce, Shopify, and Salesforce Commerce Cloud. b. Composable Agent Hub: 100s of reusable agents and templates for plug-and-play use across any API-powered system. c. Cloud Partnerships: Vultr, GCP, and Azure hosting for global agentic compute-as-a-service access. Tech Stack: Hosted on Vultr, using Groq, Llama 3, Coral Protocol, and Fetch.ai for compute, orchestration, and autonomy. Other tech: Google ADK, Next.js From prompt to production—this is how the future of work is built.

Autonomous Agents from APIs - Vultr Track
medal
GroqLlama 3.2Llama 3.1Llama 3Coral ProtocolFetch.aistreamlit

Code PRO

The code optimization and error fixing app is a powerful tool for developers and programmers that is designed to help them identify and fix errors in their code, as well as optimize it for better performance. Built using Codex, a cutting-edge AI language model, the app supports around 200 different programming languages, making it a versatile and comprehensive solution for all kinds of developers. The app provides a user-friendly interface that allows developers to easily upload their code and quickly identify any errors or issues. The app uses advanced algorithms and machine learning techniques to analyze the code and highlight any errors or bugs that may be present. It also provides suggestions and recommendations for fixing the errors, as well as optimizing the code for better performance. One of the key features of the app is its ability to provide real-time feedback as the developer is coding. This means that as the developer writes the code, the app can identify errors and provide suggestions for how to fix them. This can save developers a significant amount of time and effort, as they no longer have to spend hours debugging their code manually. The app also provides a range of other useful features, including code formatting, syntax highlighting, and autocomplete functionality. These features make it easier for developers to write code that is easy to read and understand, and that follows best practices and coding standards. Overall, the code optimization and error fixing app is a powerful and comprehensive tool that can help developers to write better code, faster. Whether you are a beginner or an experienced developer, this app can help you to identify and fix errors in your code, and optimize it for better performance.

BitsPeeps
Streamlit
application badge
Codex

SentimentSense AI

SentimentSense is an innovative AI-powered sentiment analysis app purposefully built for Monday.com's brand-new AI assistant. It offers accurate detection and analysis of emotions, specifically tailored to enhance the functionality of the Monday.com platform. By seamlessly integrating with Monday.com, SentimentSense allows users to leverage the power of AI to gain deep insights into sentiments expressed within their Monday.com items, groups, boards, and projects. In addition to its advanced sentiment analysis capabilities, SentimentSense goes beyond by providing assessment reports for selected users. These reports evaluate strengths, areas to improve, and a summary of individual users' performance within the Monday.com ecosystem. With SentimentSense, Monday.com users can effortlessly monitor and analyze customer feedback and public sentiment directly within the platform. This empowers businesses to make data-driven decisions, identify areas for improvement, and promptly respond to customer concerns, all within the familiar Monday.com environment. Utilizing advanced machine learning algorithms and natural language processing techniques, SentimentSense delivers sentiment analysis, enabling users to gauge public perception, measure brand sentiment, and uncover emerging trends. Its intuitive interface and interactive visualizations make interpreting and sharing sentiment insights seamless within the Monday.com ecosystem. In summary, SentimentSense is a purpose-built AI-powered sentiment analysis app designed to seamlessly integrate with Monday.com, providing Monday.com users with enhanced sentiment analysis capabilities to make informed decisions and gain valuable insights and suggested action items within their projects and workflows. The assessment reports further evaluate strengths, areas to improve, and an overall summary, enabling users to enhance their performance and drive better outcomes.

Appfire Team
medal
OpenAI

Ilewa

Benin, a country rich in enchanting and inspiring stories, offers a wealth of cultural treasures. Take the example of the Amazons, legendary warrior women who embody the courage and pride of the Beninese people. Their legacy is honored at the Place de l'Amazone, near the Palais des Congrès, a symbolic site where the history of these heroines continues to resonate. However, a major challenge remains: conveying this history to foreign tourists. The stories are often poorly interpreted or mistranslated, losing their essence and magic. To address this issue, we created ilewa AI. "Ilewa," meaning "our lands" in the local language (yoruba), reflects our deep attachment to our heritage. Our ambition? To make Benin the world's top tourist destination by 2030. Ilewa AI revolutionizes how Beninese stories are shared. Using our technology, content in local languages, whether audio or text, is transformed into captivating and faithful images. The benefits for tourism are immense. Visitors will have access to authentic and accurate visual representations of Beninese stories and traditions, enriching their cultural experience. They will gain a better understanding and appreciation of our heritage, increasing their satisfaction and desire to return. Ilewa AI primarily targets travel agencies, tour operators, and tourism industry stakeholders looking to offer an enriched and immersive experience to their clients. Additionally, our technology will appeal to museums, cultural centers, and educational institutions eager to promote Beninese culture to an international audience. From a business perspective, ilewa AI opens new horizons. By facilitating access to our culture, we attract more tourists, stimulate the local economy, and enhance Benin's reputation on the international stage. Investing in ilewa AI means supporting an innovative project that values our history and identity while contributing to a prosperous future for our country. Join us on this exciting journey!

IlewaAI
Streamlit
application badge
Stable DiffusionOpenAI

AI-Driven Social Media Content Optimization

Our innovative solution, powered by AI, revolutionizes social media content optimization for platforms such as Instagram, Twitter, YouTube, bloggers and podcasts. Leveraging the advanced capabilities of the Llama 2 model, we seamlessly generate hashtags for different social media posts, enhancing content discoverability. Recognizing the growing popularity of podcasts, we employ the state-of-the-art models, converting audio content into text transcripts. This integration enables podcasters to effortlessly refine their content for social sharing along with attention-grabbing descriptions and relevant hashtags. Moreover, we have incorporated the BLIP-2 model , enabling effortless conversion of images to text and extracting captivating captions. These captions are then enriched with platform-specific keywords and trending phrases, ensuring optimized engagement. We employed Open-CV framework model to process video files, transforming them into individual frames. These frames subsequently serve as inputs for the BLIP-2 and LLAMA2 model, enabling the generation of appropriate hashtags and meaningful captions. This innovation benefits both content-creators and users, as it facilitates efficient hashtag searches for desired content, enhancing the overall user experience. Overall, Experience a new era of content optimization where AI seamlessly transforms text, images, and audio into captivating social media posts, expanding reach, engagement, and impact across diverse platforms. Technical Aspects:- A web application has been built, employing AngularJS for the frontend and Flask for the backend. The application integrates Clarifai for hosting machine learning models, enabling advanced AI functions like image recognition and analysis. This fusion results in an engaging and intelligent user experience.

Kamikazee
ClarifaiLlama 2

PrithviX

PrithviX is an Adaptive AI-Driven Warehouse and Trend Forecasting System that transforms inventory management through automation, sustainability intelligence, and explainable analytics. Built on IBM Watsonx Orchestrate, it unifies social-trend detection, demand forecasting, supply-chain awareness, waste analysis, and risk simulation into one automated workflow. The process begins when Orchestrate activates PrithviX’s social-signal engine, which collects anonymized trend patterns from TikTok, Instagram, and YouTube. These signals are cleaned and validated to separate real demand from short-term hype. The refined signals, combined with historical sales logs, feed into the forecasting engine to produce short- and medium-term predictions. SHAP explainability reveals which factors influence each forecast, increasing clarity and trust. Orchestrate then connects these predictions to the supply-availability agent, which evaluates stock levels, shipment delays, expiry risks, and supplier reliability. This ensures insights match real operational constraints. PrithviX’s sustainability module analyzes carbon footprint, packaging impact, waste probability, and deadstock risk to support responsible decisions. A simulation engine models thousands of possible outcomes, estimating risks related to overstocking, lost revenue, waste generation, and environmental impact. All outputs flow into an XAI decision card presenting trends, supply feasibility, sustainability impact, and risk levels. Managers receive one clear recommendation: stock more, stock less, or wait. PrithviX stands out by combining trend intelligence, forecasting, supply logic, sustainability scoring, and risk modeling into a single orchestrated ecosystem. It supports SDG 9 by modernizing warehouse operations, SDG 12 by reducing waste, and SDG 17 by integrating with ERP systems like SAP and Oracle. The result is a smart, transparent, and sustainable warehouse intelligence platform.

Search Engine
IBMLlama 3.2

SoulSync -AI Powered Personality Driven Dating App

SoulSync is a next-generation dating application designed to foster meaningful relationships by leveraging psychological insights and AI technology. The app addresses the challenge of superficial matching algorithms in traditional dating apps by incorporating scientifically validated metrics: MBTI personality types, Big Five personality traits, and shared hobbies. During sign-up, users provide their MBTI type, select hobbies from a predefined set, and complete a Big Five personality assessment. SoulSync then calculates compatibility scores for each user pair based on: ✅ Researched psychological match scores for all 256 MBTI combinations. ✅ Embeddings for hobbies to measure shared interests. ✅ Big Five trait similarities to ensure alignment in core personality dimensions. The app uses a weighted scoring system to recommend the top 3 matches for each user, ensuring highly personalized suggestions. The weights are assigned based on research-backed methodologies, such as: Personality traits (Big Five) and shared interests (hobbies) being strong predictors of relationship satisfaction (Finkel, E. J., Eastwick, 2005) MBTI compatibility being widely used in relationship counseling to predict interpersonal dynamics (Myers, I. B., & Myers, P. B., 1995). Once a match is accepted, users can engage in conversations with AI-powered chat assistance, powered by DeepSeek, to help craft thoughtful and engaging messages. This feature ensures users can break the ice and maintain meaningful conversations effortlessly. Features: ✅ Smart Matching – Uses MBTI & Big Five for accurate compatibility (OpenAI Embeddings). ✅ AI Chat Assist – DeepSeek AI suggests messages to keep chats engaging. ✅ Personalized Matches – Combines hobbies & traits for better connections. ✅ Scalable Tech – Can power AI ads & behavior tracking. Broader Applications: ✅ Smart Ads: Personalized suggestions based on traits & hobbies. ✅ Behavior Insights: Tailored experiences in education, healthcare & more.

Brain404
OpenAIDeepSeek R1AI/ML API

Liquid LMS

The Problem: Traditional education has not changed much in the last century, and it fails to meet the diverse needs of students. One-size-fits-all teaching methods, outdated curricula, and limited access to resources often result in disengaged students who are unprepared for the workforce of tomorrow. The Solution: We propose a revolutionary approach to education that integrates AI and new technology. By leveraging the power of AI, we can create personalized learning experiences that cater to each student's unique needs, interests, and abilities. The Implementation: Our approach is built on three pillars: a. Adaptive Learning: Our AI-powered algorithms will analyze each student's performance data to create a customized learning path. This will help students learn at their own pace and achieve better learning outcomes b. Immersive Learning: We will use virtual and augmented reality to create immersive learning experiences. This will enable students to explore complex concepts in a more engaging and interactive way. c. Collaborative Learning: We will facilitate collaborative learning by leveraging AI-powered tools that enable students to work together on projects and assignments in real-time. The Benefits: Our approach to education will offer several benefits, including: a. Improved Learning Outcomes: Personalized and engaging learning experiences will help students achieve better learning outcomes and prepare them for the workforce of tomorrow. b. Cost-Effective: Our AI-powered approach to education will be cost-effective as it will reduce the need for physical classrooms and expensive resources. c. Accessible: Our approach will be accessible to all students regardless of their location, socioeconomic status, or learning abilities. Our approach to education will revolutionize the way we teach and learn. By leveraging the power of AI and new technology, we can create personalized, engaging, and cost-effective learning experiences that prepare students for tomorrow.

PlayFine
WhisperDALL-E-2GPT-3

Carbon Twin

CarbonTwin revolutionizes how organizations measure, manage, and reduce their carbon emissions by combining blockchain transparency, digital twin simulations, and advanced AI. In today’s global supply chains, carbon tracking is often fragmented, inaccurate, and open to manipulation. CarbonTwin addresses this by leveraging blockchain to create immutable, tamper-proof emission records, ensuring trust and traceability from raw material sourcing to product delivery. Every transaction, emission report, and carbon credit is securely stored on-chain, providing unmatched transparency and accountability. Beyond secure tracking, CarbonTwin empowers businesses with digital twin simulations. These real-time, virtual models of facilities and supply chains allow organizations to forecast carbon impacts, test reduction strategies, and run predictive analyses before implementing them. This transforms sustainability planning from guesswork into data-driven decision-making, enabling companies to identify cost-effective and impactful solutions. At the heart of CarbonTwin lies ChatGPT-5 AI, delivering advanced intelligence. From automated emission verification and fraud detection to personalized optimization recommendations, CarbonTwin provides enterprises with deep insights that drive measurable progress. The platform also streamlines compliance with automated ESG reporting, reducing regulatory burdens while ensuring accuracy. With a real-time dashboard, multi-facility monitoring, interactive analytics, and proactive alerts, CarbonTwin delivers both the big picture and detailed insights. Whether for enterprises aiming to decarbonize, carbon credit traders seeking verified transparency, or consultants modeling client impact, CarbonTwin provides the tools to act with confidence and accelerate toward a sustainable future.

CoOlDuO
Vercel
application badge
GPT-5

Report Cruncher

Report Cruncher is a cutting-edge financial analysis platform designed to simplify financial reports for retail investors. Report Cruncher provides powerful insights through machine learning to empower retail investors to make informed decisions and achieve success in the stock market. The platform is user-friendly, accessible, and designed to meet the unique needs of retail investors at every level of expertise. By leveraging the GPT-3 Curie model fine-tuned with the ECTSum dataset, Report Cruncher can provide users with easy-to-understand financial data, allowing them to quickly identify the most important information in a report. The advanced machine learning algorithms and user-friendly interface make it the perfect tool for anyone looking to make informed investment decisions. Report Cruncher's success depends on attracting and keeping subscribers through a subscription-based model. The platform is designed for retail investors, defined as nonprofessional investors who use their own money to buy and sell securities. Retail investors accounted for more than 20% of all stock market shares traded and accounted for more than $84 trillion in trades in 2021. With a subscription model, Report Cruncher will provide a sustainable revenue stream while empowering retail investors to make informed decisions in the stock market. The platform is constantly evolving, with plans to introduce chained prompts, a series of prompts that build on each other to produce a final summary, to provide users with more in-depth analysis and a more comprehensive understanding of the financial reports they're analyzing. With sufficient funding, the team plans to fine-tune the Davinci model to get even better results.

AI-DATA-TOOLS
medal
ChatGPTGPT-3

VIsionAid

VisionAid is an AI-driven medical assistant designed to empower blind and visually impaired individuals by providing critical insights from medical data, all through voice-controlled, hands-free interactions. The app’s capabilities include interpreting complex medical images like X-rays, MRIs, and CT scans, translating visual data into clear, accessible language that users can understand. This feature enables users to receive essential health information without needing to rely on visual aids or third-party assistance. With VisionAid, users can also gain detailed insights from prescriptions. The app reads out medication names, dosages, and instructions, ensuring users have complete knowledge of their treatment plans. If a prescription includes any special precautions, side effects, or drug interactions, VisionAid can convey this information effectively, promoting safe medication use and informed healthcare decisions.The app is fully voice-activated, allowing users to ask questions and receive responses without ever needing to touch a screen. From asking, “What’s in my prescription?” to “What does my X-ray show?” VisionAid offers a seamless, conversational experience. Through sophisticated text-to-speech and speech recognition technology, it interprets queries and delivers responses in a clear, natural voice. In addition to image and prescription analysis, VisionAid can assist users in managing schedules by setting medication reminders, doctor’s appointments, and follow-ups, all accessible through simple voice commands. This functionality supports users in maintaining their health routines with minimal effort. Designed with the unique needs of visually impaired users in mind, VisionAid’s combination of advanced AI, intuitive voice control, and comprehensive healthcare insights represents a significant step toward accessible, independent healthcare management.

TrioVibians
Vercel
application badge
VercelRhymes.ai

AI Powered Mesh Network

AIM Network is an AI-powered application designed for network engineers, integrating seamlessly with existing monitoring tools and network logs. It automates troubleshooting, provides real-time solutions, and enhances operational efficiency while reducing downtime. By leveraging advanced AI technologies like machine learning and predictive analytics, AIM Network optimizes network performance and empowers engineers with actionable insights for proactive management. Core Components Zabbix Dashboard AIM Network integrates with Zabbix, an enterprise-class open-source monitoring solution, offering: Advanced distributed monitoring for servers, networks, and applications. Real-time notifications and alerting. Extensive data collection options (e.g., SNMP, IPMI, JMX). Customizable dashboards and visualization tools. Auto-discovery of network devices and configurations. AI Assistant The AI-powered assistant enhances troubleshooting efficiency with: Intelligent Log Analysis: Automatically identifies patterns and anomalies in network logs. Root Cause Analysis: Pinpoints underlying causes of issues, not just symptoms. Step-by-Step Resolution: Provides actionable guidance to resolve problems. Network Best Practices: Recommends solutions based on industry standards. Knowledge Base: Continuously learns from new issues to improve recommendations. Reduced Downtime: Speeds up issue resolution to minimize disruptions. Key Features Seamless integration with monitoring tools and logs. Real-time troubleshooting and resolution of network issues. AI-powered insights for proactive network management. Optimization of network performance, including speed, bandwidth, and reliability. Ability to answer general network questions using network documentation. Whether addressing latency, connection problems, or bandwidth constraints, AIM Network empowers engineers with expert-level recommendations, ensuring efficient and reliable network operations.

AIM Network
LangChainGroqLlama 3.2streamlitReplit

TalentPilot

Core Engine: IBM watsonx Orchestrate serves as the "Brain," managing the agent's lifecycle, tool connections, and reasoning logic. We utilized the ReAct (Reason + Act) framework, allowing the agent to break down complex user queries into a chain of logical steps (e.g., Step 1: Check Budget. Step 2: Check Policy. Step 3: Formulate Answer.). Knowledge Base: A hybrid ingestion model was used. Unstructured: PDF documents for policies (Leave_Policy.pdf, Hiring_Plan.pdf) enable Retrieval-Augmented Generation (RAG) for answering qualitative questions. Structured: CSV files (employee_data.csv, recruitment_data.csv) provide the quantitative data needed for analytics. Frontend & Deployment: To demonstrate enterprise scalability, we built a custom frontend using Next.js (React). This application acts as a secure interface for the agent. Security: The app uses Next.js API Routes to securely exchange the IBM Cloud API Key for a short-lived IAM Token on the server side. This ensures that sensitive credentials are never exposed to the client browser. Hosting: The entire solution is deployed on Vercel, providing a globally accessible, responsive interface that can be used on any device. Impact & Innovation TalentPilot represents a shift from "Passive HR" to "Active Orchestration." By automating the low-level work of policy checking and data retrieval, it frees up HR professionals to focus on what really matters: people strategy and culture. It ensures 100% compliance with dynamic company rules (like hiring freezes) and provides instant, data-driven answers that would normally take a human analyst hours to compile. This project demonstrates the true potential of Agentic AI: systems that don't just talk, but help us run our businesses better.

RECURSE
Vercel
application badge
watsonx.aiIBMIBM GraniteLlama 3.1Generative AgentsVercel

AI Home Design

AI Home Design is an interior design assistant powered by Stable Diffusion and YOLO to solve pain points felt by homeowners. It differs from other AI interior design apps out there because 1) it addresses pain points in homeowners' entire user journey, 2) functions as a social sharing platform, and 3) is an aide to augment, not replace home decor professionals and designers. FIRSTLY, the flagship "Create With AI" feature guides the user in prompt engineering to convert their design hunches from text to actual image, helping them overcome creative blockages. This also improves communication with interior designers, since words can be subjective, but images are direct. SECONDLY, homeowners may want to reimagine a space even after initial fittings like paneling and paint jobs are already done. They cannot tear down these fittings in real life, but they can use Stable Diffusion's image-to-image functionality to reimagine the space. THIRD, AI Home Design also functions as a social sharing platform where users can draw inspiration and start conversations with one another. FINALLY, homeowners still need to furnish and populate their spaces even after they have decided on their designs. This is where YOLO comes in, helping the user to recognise objects, and creating outbound e-commerce links for them to buy items. AI is thus used here to smoothen homeowner-professional interactions and engender connections. Even after the hackathon, I am continually improving the app by creating new features (see slide deck!), such as tools to facilitate discussions, recommenders, or improved object detection. On the technical front, I aim to infuse more powerful models like CLIP, Segment Anything or YOLOv8. On the business front, I am building in-app services to serve new target groups like real estate agents and elder-friendly/disability-friendly retrofitting specialists. Join me on this journey to make interior design more seamless for users, and to use AI in a coherent, impactful way.

W Tan
medal
Vercel
application badge
Stable DiffusionVercelYOLOv5

PropLlama ai

PropLlama.ai is a real estate platform designed to transform the daunting and intricate task of navigating the property landscape into a seamless and enjoyable experience. Our platform features an intelligent chatbot that understands, remembers, and responds to your queries like a trusted friend, making it feel like you are having a meaningful conversation with a property confidant rather than just another chatbot. Additionally, our platform offers 24/7 chat support with a team of seasoned experts, personalized property searches, insightful decision-making support, comprehensive assistance throughout the property acquisition process, and meticulous legal compliance support. This includes everything from document verification to crafting customized lease agreements. With PropLlama.ai, you get convenience, speed, and accuracy at your fingertips, making it your ultimate real estate companion and doubt resolver. Say goodbye to data overload, questionable broker integrity, and the stress of legalities. PropLlama is here to guide you through it all. The core of PropLlama.ai is powered by the Llama-13b-alternative chat model(tested with Llama-70b too) and Clarifai. It enables the chatbot to understand the context of a conversation, remember previous interactions, and generate human-like responses. It can also process text data, such as property descriptions, legal documents, and news articles, to extract relevant information and provide personalized recommendations to users. Langchain Agents and LLMs- Various tools which were built using Llama and Clarifai for variety of class of queries were intergrated using Langchain agents. LangChain is a framework designed to simplify the creation of applications using large language models (LLMs) In summary, PropllAma.ai leverages advanced technologies, such as the Llama-13b-alternative chat model, Clarifai platform, Llama-70b model for testing, and Langchain agents and LLMs,

LlamAI Agents
Streamlit
application badge
ClarifaiLlama 2LangChainGPT-3.5

Granite-AI Market Navigator

𝐏𝐫𝐨𝐛𝐥𝐞𝐦 𝐒𝐭𝐚𝐭𝐞𝐦𝐞𝐧𝐭: Businesses and investors struggle to stay updated with real-time market trends, often relying on outdated or fragmented data sources. Traditional analysis methods lack AI-driven insights, making it difficult to anticipate risks and opportunities efficiently. 𝐒𝐨𝐥𝐮𝐭𝐢𝐨𝐧: Granite-AI Market Navigator addresses this gap by using the Bing News API to fetch real-time news and IBM Granite AI models (Granite-13b-Instruct-V2) to analyze sentiment. This AI-powered solution visualizes market trends through an interactive sentiment thermometer and provides AI-generated investment recommendations. 𝐊𝐞𝐲 𝐅𝐞𝐚𝐭𝐮𝐫𝐞𝐬 & 𝐅𝐮𝐧𝐜𝐭𝐢𝐨𝐧𝐚𝐥𝐢𝐭𝐢𝐞𝐬: ⿡ 𝐑𝐞𝐚𝐥-𝐓𝐢𝐦𝐞 𝐌𝐚𝐫𝐤𝐞𝐭 𝐍𝐞𝐰𝐬 𝐅𝐞𝐭𝐜𝐡𝐢𝐧𝐠: . Users input keywords related to business trends. . The system fetches the latest news using the Bing News API. . Displays 5-10 relevant articles with summaries and direct links. ⿢ 𝐈𝐁𝐌 𝐆𝐫𝐚𝐧𝐢𝐭𝐞 𝐀𝐈-𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐒𝐞𝐧𝐭𝐢𝐦𝐞𝐧𝐭 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬: Analyzes news headlines and summaries using IBM Granite-13B-Instruct-V2. Determines sentiment categories: Positive, Neutral, or Negative. Displays an AI-driven sentiment thermometer (Hot = Trending, Cold = Low Impact). ⿣ 𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐈𝐧𝐬𝐢𝐠𝐡𝐭𝐬 & 𝐃𝐞𝐜𝐢𝐬𝐢𝐨𝐧 𝐀𝐬𝐬𝐢𝐬𝐭𝐚𝐧𝐜𝐞: Provides AI-powered recommendations based on sentiment trends. Example: High positive sentiment → Investment Opportunities.

GenAI Innovators
Vercel
application badge
IBM GraniteIBMVercelIBM watsonx Assistant

GemInsights

GemInsights: Transforming Startup Analytics with AI Efficiency In the fast-paced startup environment, extracting actionable insights from data efficiently is a constant challenge. GemInsights, an innovative analytics platform, addresses this by automating Exploratory Data Analysis (EDA) and minimizing the need for an extensive data analyst team. This comprehensive solution integrates cutting-edge technologies like Gemini AI, Trulens, and Vertex AI to redefine how startups approach data-driven decision-making. Objectives: GemInsights has clear objectives: reduce time spent on EDA, optimize costs associated with data analysts, provide actionable insights, and integrate advanced technologies seamlessly. Technological Foundations: Leveraging Gemini AI, GemInsights automates complex analytical tasks. Trulens enhances visualization for clearer data interpretation, while Vertex AI serves as the backbone for deploying and managing machine learning models. User Experience: GemInsights automates EDA processes, handles null values intelligently, and generates intuitive visualizations. This streamlines decision-making by translating insights into actionable recommendations. Impact on Startups: GemInsights directly impacts budget allocation, reduces time-to-market, fosters innovation, and ensures scalability. It empowers startups to reallocate funds strategically, respond rapidly to market changes, drive innovation, and scale efficiently. Future Developments: The platform's roadmap includes ongoing enhancements in machine learning models, compatibility with diverse data sources, and integration with emerging technologies. The goal is to continually empower startups with the latest advancements in data analytics. Conclusion: GemInsights is more than a platform; it's a strategic enabler for startups navigating the data landscape. By automating EDA, optimizing costs, and providing actionable insights, GemInsights transforms how startups approach data-driven decision-making.

Binary Bandits
Streamlit
application badge
TruLensGemini AIGenerative AI Studio

GPT-Swarm

GPT-Swarm is a groundbreaking project that combines swarm intelligence and advanced language models to tackle complex tasks across diverse domains. Our innovative framework is robust, adaptive, and scalable, outperforming single models by leveraging the power of collective problem-solving and distributed decision-making. Not to mention the lightning-fast speed with which it performs the research. Our team has meticulously designed GPT-Swarm to be adaptive, responsive, and efficient, capitalizing on the collective intelligence of numerous GPT models working synergistically. By having these models collaborate, we can significantly enhance performance and deliver superior results compared to traditional methods. In one of our primary use cases, we have deployed GPT-Swarm to conduct comprehensive background checks on startups and idea spaces. This process involves evaluating their credibility, financial stability, and potential for growth, ensuring a well-rounded understanding of each venture's viability. Our innovative approach allows for a more in-depth analysis, equipping investors and stakeholders with invaluable insights for better decision-making. By submitting GPT-Swarm to this hackathon competition, we aim to showcase the immense potential of swarm intelligence in transforming the landscape of artificial intelligence and machine learning. Our project not only highlights the power of collaboration among GPT models but also sets a new benchmark for tackling complex tasks and challenges. Join us as we embark on this exciting journey towards a more intelligent and interconnected future.

AutoSwarm
medal

Financial Advisor

Managing finances can be challenging in today's world due to various factors such as economic downturns, inflation,and conflicts. Rising prices, particularly for energy, make it difficult for people to spend their money reasonably. With so many products, suppliers, and options to consider, it can be overwhelming for those with little experience in spending. To tackle these issues, our team has come up with the "Financial Advisor," a chatbot that helps users spend their money more efficiently and effectively. Our solution is based on three main features: firstly, listing items to buy within a certain spending limit and marketplace, which is fine-tuned using GPT-3 to provide customized and optimized advice tailored to each user's requirements. Secondly, we help users plan their spending by allocating appropriate budgets for various needs such as food, entertainment, education, and commuting. Lastly, we remind users not to overspend on sale days to maintain their financial stability. Our business model involves collecting user data to help them access products that are right for them while earning revenue from advertising. We plan to integrate our solution into banking apps to support users in managing monthly expenses, setting up savings funds, and getting monthly bank fees. We are building a new advertising system that benefits users the most by considering their financial optimization criteria and analyzing their needs. We also provide monthly spending transaction statistics to help users know where they stand financially and offer advice on their spending. In summary, our Financial Advisor solution helps users make the most optimal and reasonable spending choices while staying within their budget. It saves time and effort in market research, enhances the user experience with a user-friendly interface, and provides a new advertising system that benefits users the most. Our solution revolutionizes the way people spend their money, improving their financial stability.

Horros
medal
Vercel
application badge

PolicyPath

PolicyPath tackles one of healthcare's biggest bottlenecks: prior authorization (PA) for oncology treatments. Currently, obtaining approval for cancer therapies takes days or weeks, delaying critical care and frustrating patients, providers, and payers alike. Manual review of clinical documents, insurance eligibility, and complex policy criteria is error-prone, costly, and slow. Our solution automates the entire PA workflow end-to-end. PolicyPath ingests clinical notes (PDFs), patient demographics, and insurance data from Google Sheets, extracts structured clinical information using OCR and AI, validates insurance eligibility in real-time, and applies payer-specific policy rules to generate instant approve/deny/review decisions. Complex or ambiguous cases are intelligently routed to human reviewers, with all actions logged for compliance and auditability. The system uses Opus for orchestration and agentic AI-powered workflow automation, Lovable for a polished React frontend, and Google Sheets as a lightweight data source. Every decision includes a detailed rationale, failed criteria analysis, and a comprehensive audit log exported to a tracking ledger for transparency and regulatory compliance. PolicyPath reduces approval times by up to 95%, cuts administrative costs, improves patient outcomes by accelerating access to life-saving treatments, and provides payers with defensible, auditable decisions. Our MVP handles real-world oncology cases with biomarker requirements, prior therapy validation, and cost thresholds—demonstrating scalability to other specialties and payers. This is healthcare automation that works for everyone: faster, fairer, and fully traceable.

Team Apollo
Opus

AI-Driven Zabbix for School Networks

Our project integrates AI with Zabbix to develop an intelligent network monitoring and diagnostic system tailored for educational institutions. Schools rely heavily on stable internet connectivity for digital learning, online assessments, and cloud-based applications. However, network issues such as downtime, high latency, or bandwidth constraints can disrupt these activities. To address this, we enhance Zabbix with AI-powered analysis using Orca Mini and GPT-4. Our system detects, analyzes, and diagnoses network problems in real time, providing automated insights and recommendations to IT administrators. The AI assistant runs on Windows, communicating with a Zabbix server on Ubuntu via SSH, ensuring seamless interaction between AI and network monitoring tools. When an issue arises, Zabbix detects the alert, and the AI assistant processes logs, configurations, and network metrics to determine potential root causes. It then generates detailed recommendations for resolution, helping IT teams act faster and prevent prolonged downtime. The system also supports predictive analytics, identifying trends that may lead to future network failures and suggesting proactive solutions. This AI-enhanced network management drastically reduces IT workload, optimizes resource allocation, and ensures continuous, high-quality connectivity for students, teachers, and administrators. By making network troubleshooting faster and smarter, our project empowers schools with self-healing, AI-driven infrastructure that supports modern education and digital transformation. 🚀

IAlovers
ChatGPTMetaGPTLlama 3

TechnoForge Automotive

Technoforge Automotive is a company that specializes in car design using the latest and most advanced technologies. It uses Stable Diffusion, GPT, and Segment Anything to create a powerful and efficient platform for designing cars. Stable Diffusion is an innovative and cutting-edge technology that allows designers to create high-quality and realistic images of cars using natural language inputs. It uses the open-source state-of-the-art text-to-image model to generate art using natural language. This technology is essential for creating realistic images of cars that can be used for various purposes, such as marketing and advertising, product design, and research and development. GPT is a natural language processing technology that helps designers communicate their ideas. It interprets user inputs, making it easier for designers to express their ideas in natural language. GPT is critical in ensuring that the car design tool is user-friendly and intuitive, enabling designers to communicate their ideas quickly and easily. Segment Anything is another technology used by Technoforge Automotive, which is a new task, model, and dataset for image segmentation. It enables designers to segment any object in the image, allowing them to manipulate and modify the image as needed. By using Segment Anything, designers can make changes to the design quickly and easily, ensuring that the final product is optimized for performance and efficiency. By utilizing Stable Diffusion, GPT, and Segment Anything, Technoforge Automotive can help designers create innovative and unique car designs that are optimized for performance and efficiency. These technologies work together to create a powerful and efficient platform for designing cars, ensuring that designers have all the tools they need to bring their ideas to life.

team phoeniks
GPT-4GPT-3