Jaswir Raghoe@Jaswir

AI Game Maker turns a single sentence into a complete, playable 2D pixel-art platformer in about 60 seconds no engine knowledge, no art skills, no team required. You type something like "a sneaky raccoon in a moonlit junkyard" and the system generates a themed 16-cell spritesheet, walk and jump animations, an original BGM track, procedural SFX, and a fully validated platformer level all coherent, all playable, right in your browser. Under the hood, Claude Code acts as the orchestrator brain, routing tasks to a five-skill pipeline (design, spritesheet, animation, level, audio) powered entirely by Gemini. The level generator doesn't just place random platforms every level passes a physics reachability simulation before it's delivered, ensuring every jump fits the player's arc and there's always a path to the goal. The studio includes six tabs: a live game preview (arrow keys + space), a drag-and-drop level editor, a per-cell sprite pixel editor, animation strip previews, an audio player, and a raw JSON code view. Games are shareable via embeddable links. AI Game Maker is live at aigamemaker.studio, deployed on a Vultr VPS with nginx and systemd. It's built by Jaswir Raghoe, a full-stack AI engineer based in The Hague, Netherlands 1st place at AI House Amsterdam and a frequent global hackathon finalist.

Most founders don’t fail because they can’t build — they fail because they spend weeks researching trends, debating ideas, and hesitating before launching. That delay kills momentum and makes product-market fit feel distant and expensive. Our solution is an OpenClaw skill that autonomously discovers real B2B pain points, generates a focused website or MVP around the opportunity, and deploys it instantly to Vercel. Instead of spending 2–4 weeks validating an idea, founders can launch in minutes, test demand immediately, and iterate based on real user feedback. By dramatically shortening the cycle from idea to live product, this tool accelerates the path to product-market fit and unlocks faster revenue opportunities. From landing-page lead generation to micro-SaaS subscriptions that can scale into recurring monthly income.

According to the Animal Humane Society, cats are crepuscular, meaning their activity peaks during dawn and dusk. Anecdotal evidence supports this, with many owners reporting their cats being awake late into the night or very early in the morning. While humans attempt to get some shuteye, this leads to an unsupervised environment where our feline friends may be up to some tomfoolery… Enter PetGuard, the Gemini-powered robotic assistant that keeps your pet safe and out of trouble! We have used Vector, the robot developed by Anki, which has been augmented with Gemini to track your cat, scan the environment for potential hazards and use auditory cues to divert its attention. Using a virtual environment, we have simulated a virtual instance of Vector, a virtual instance of a cat that mimics its behavior, as well as the most common household hazards the pets are prone to. Using this simulation we have finetuned our robot assistant to ensure that it is as robust as possible, finally giving pet owners the peace of mind that they deserve!

LazyNest is an AI-powered home-hunting assistant designed to solve the housing shortage challenge starting in the Netherlands, where over 400,000 homes are missing and buyers must act within hours to secure a viewing. Our system of intelligent agents continuously crawls property sites, filters listings based on personal criteria, scores them with AI, and instantly books viewings—giving house-seekers a real speed advantage in a hyper-competitive market. By automating the search and booking process, LazyNest reduces stress, saves time, and helps buyers beat the crowd. After launching in the Netherlands, we plan to scale across Europe and eventually worldwide, bringing fast, automated home discovery to millions of seekers each year. Users begin by answering a conversational, multi-step questionnaire that defines their ideal property criteria (location, budget, bedroom count, size, etc.). These criteria are then fed into an Opus-powered Crawler Workflow, which monitors real estate websites 24/7. When a matching listing appears, LazyNest instantly surfaces it through a clean, modern interface. With one click, users can book viewings for individual properties—or all matched properties at once. The Opus Booking Workflow handles the entire communication flow behind the scenes, ensuring users are among the first to request a viewing. LazyNest supports English and Dutch, features a responsive UI, and is engineered with a powerful server-centric architecture using Next.js Server Actions. While Genkit currently supports type definitions, the system is designed for future AI-driven enhancements like automated property summarization and smart input validation. * Technology & Category Tags Tech Stack: Next.js (App Router, Server Components) TypeScript Tailwind CSS shadcn/ui Opus Workflows (Crawler + Booking) Vercel Hosting Categories: Real Estate Tech AI Automation Productivity Workflow Automation Web Application Property Search Booking Systems

The open web is at a critical turning point. AI agents powered by large language models now browse and summarise web content at massive scale—hundreds of pages per second—yet generate no revenue for the publishers who create it. This silent extraction of value threatens the economic foundation of quality online content. Publishers face collapsing incentives: AI systems harvest their intellectual property without paying, eroding the motivation to keep information freely available. Without intervention, the open web risks fragmentation, as creators retreat behind paywalls or shut down entirely. WebFlow Protocol offers a bold solution. It introduces a decentralised micropayment system that allows AI agents to compensate publishers automatically and transparently. Each website adds a payment address to its robots.txt file. When an AI agent visits, it detects the address and triggers an instant micropayment before accessing content—frictionless and fair. A future authentication gateway will ensure only compliant agents receive access. The opportunity is enormous. The global digital advertising market surpassed $626 billion in 2023, with up to $120 billion in publisher revenue now vulnerable to AI-driven content scraping. As AI adoption accelerates, establishing a standard for ethical, compensated access is both urgent and achievable. WebFlow Protocol aligns the interests of publishers and AI developers, creating a sustainable ecosystem where innovation and fairness coexist. By embedding monetisation directly into web infrastructure, it ensures the creators who sustain the open web are rewarded in the AI era. The message is clear: we must evolve the web’s business model to preserve openness, diversity, and quality. Through WebFlow Protocol, we can keep the internet open—not just for people, but for the intelligent systems that increasingly shape our digital future.

𝗗𝗲𝗲𝗽𝗟𝗼𝘃𝗲 𝗔𝗜: 𝗥𝗲𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝗶𝘇𝗶𝗻𝗴 𝗠𝗼𝗱𝗲𝗿𝗻 𝗗𝗮𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗔𝗜 𝗗𝗲𝗲𝗽𝗟𝗼𝘃𝗲 𝗔𝗜 is an intelligent dating assistant designed to eliminate awkward silences, boost confidence, and enhance communication skills. The platform leverages cutting-edge AI models, including 𝗗𝗲𝗲𝗽𝗦𝗲𝗲𝗸 𝗥𝟭, 𝗢𝗽𝗲𝗻𝗔𝗜 𝗪𝗵𝗶𝘀𝗽𝗲𝗿 𝘃𝗶𝗮 𝗔𝗜/𝗠𝗟 𝗔𝗣𝗜 𝗸𝗲𝘆, and the 𝗟𝗟𝗮𝗠𝗔 𝗩𝗼𝗶𝗰𝗲 𝗠𝗼𝗱𝗲𝗹, to provide users with real-time conversation guidance, AI-driven flirting strategies, and safety insights. 🟢 𝗞𝗲𝘆 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀: 𝗔𝗜 𝗩𝗼𝗶𝗰𝗲 𝗔𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁 – Engage in seamless, natural conversations with AI-powered voice interaction. 𝗥𝗲𝗱 𝗙𝗹𝗮𝗴 𝗥𝗲𝗽𝗼𝗿𝘁 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 – Detects potential risks in chats and provides detailed safety insights. 𝗥𝗲𝗮𝗹-𝗧𝗶𝗺𝗲 𝗗𝗮𝘁𝗶𝗻𝗴 𝗦𝗰𝗲𝗻𝗮𝗿𝗶𝗼 𝗦𝗶𝗺𝘂𝗹𝗮𝘁𝗼𝗿 – Helps users practice and refine their conversational skills in a risk-free environment. 𝗔𝗜 𝗙𝗹𝗶𝗿𝘁𝗶𝗻𝗴 𝗖𝗼𝗮𝗰𝗵 – Personalized coaching tailored to different dating styles, from playful banter to deep emotional connections. 𝗖𝗼𝗻𝗳𝗶𝗱𝗲𝗻𝗰𝗲 𝗕𝗼𝗼𝘀𝘁𝗲𝗿 – AI-driven training to help users overcome social anxiety and master real-life dating interactions. What sets 𝗗𝗲𝗲𝗽𝗟𝗼𝘃𝗲 𝗔𝗜 apart is its ability to adapt to different dating styles, offering personalized coaching and real-time assistance that ensures conversations stay engaging and effortless. The platform is deployed on Vercel, with a React.js frontend and Python-based AI processing, ensuring a smooth and responsive user experience. By combining AI-powered coaching, real-time feedback, and advanced conversational insights, 𝗗𝗲𝗲𝗽𝗟𝗼𝘃𝗲 𝗔𝗜 transforms dating into a stress-free, enjoyable experience, empowering users to communicate with confidence, detect red flags, and build meaningful connections. 🚀

Offline Edubot is a revolutionary AI-based tutor built to bridge the education gap in regions with poor or no internet connectivity. By leveraging preloaded content and advanced AI technologies like Natural Language Processing and Machine Learning, Offline Edubot delivers personalized learning experiences to students in remote or underserved communities. Designed to function entirely offline, this solution provides access to a wide range of subjects while adapting to each student's learning pace. With a focus on scalability, the platform plans to expand into multilingual support and integrate regional curricula to meet the needs of different countries. A key future goal for Offline Edubot is to integrate Wikipedia data into the chatbot, enabling users to access a vast library of knowledge offline. This enhancement will make the platform even more comprehensive, offering a wide range of educational resources without the need for internet connectivity. In addition, we plan to collaborate with governments and charitable organizations, adopting a sustainability model similar to Wikipedia’s, ensuring that education remains free and accessible to all. Whether it's supporting education during natural disasters or empowering adult learners in vocational training, Offline Edubot aims to become the go-to solution for offline learning, bringing education to every corner of the world. For the future we plan entirety of Wikipedia to be available. People can upload notebooks also

Flow LearningLab helps students by answering questions, providing explanations, and offering study recommendations based on their unique needs. It addresses the challenges students face, such as understanding complex materials and hesitancy in asking for help, by breaking down problems and adapting to each student’s learning style. The ultimate goal is to make high-quality, personalized tutoring accessible to every student, empowering them to overcome learning obstacles and achieve their full potential. By providing a safe, judgment-free learning environment, Flow LearningLab encourages students who might be shy or afraid of asking questions in traditional classroom settings to confidently seek the help they need. This transformative approach has the potential to revolutionize the educational experience, making personalized support a cornerstone of student success. An intelligent personal academic tutor that leverages Langflow, Vectara, and CustomGPT. This assistant is integrated with Azure endpoints to offer personalized, real-time academic support and guidance. Langflow structures the interaction logic, Vectara enhances query understanding and context, and CustomGPT provides a seamless, conversational interface

Universal Startup kit is designed to eliminate the initial setup hassles for hackathon teams and developers, the Universal Startup Kit streamlines the creation and management of essential resources through an intuitive Streamlit interface. Features: 🐈‍⬛ Creates Github Repo 👾 Creates Discord Server for your team 📝 Creates Trello Kanban Board to keep track of your tasks and progress 🙌 Adds Collaborators to your Github Repo and Trello Board Under Construction: 📅 Creates Schedule for your team using Google Sheets 🍹 Slack for your team Lablab.ai: This product would be highly beneficial to lablab.ai it would allow participants to setup easily and focus more on development, engagement and innovation and benefit the lablab brand. Users can quickly configure these tools by inputting their API keys once. The Universal Startup Kit not only helps teams start their projects faster but also supports them in maintaining focus on innovation and development tasks right from the onset. With its comprehensive feature set, the Universal Startup Kit is poised to become an indispensable asset for any team looking to optimize project setups and foster effective collaboration from day one

⏱️ Build the next generation of Autonomous Agents in the heart of Europe’s AI Revolution. 📅 May 13 – 20, 2026 May 13 – 19: Online Build Phase. May 19: An exclusive on-site build day at Milan AI Week for selected participants. May 20: Awards Ceremony. 📍On-site Venue (May 19–20): Fiera Milano (Rho), Milan, Italy 🤝 Join solo or with a team. 🎟 FREE Milan AI Week conference ticket included for participants. 💰 $32,000+ prize pool 🧑‍💻 Apply now to turn your autonomous agent into a market-ready enterprise solution.

Join our $1,000,000+ startup challenge series powered by Surge 📌 This announcement outlines the launch of a Global Human+AI Exchange — aligning universities, global cities, talent networks, and industry to accelerate human-centered AI innovation, technology transfer, and economic growth. 👉 Read more here ⏱️ 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. 🕙 Doors open at 10:00 AM, first come, first served. • 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 📲 Real-time on-site updates (SF) For real-time announcements and information during the on-site portion (Feb 14–15), join the LabLab SF Chapter WhatsApp group: 👉 Join the WhatsApp group 🤝 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.

⏱️ 4 weeks to design and ship a working Web3 product or AI agent. 📅 February 4 to March 1, 2026 • Feb 4 – Hackathon opens. Teams can start building and submitting. • Feb 5 to March 1 – Build, test, and iterate. • March 1 – Final submissions due. 🚨 Important eligibility reminder To be eligible for prizes, teams must post their submission video on X and tag @lablabai and @Surgexyz_. 🤝 Build solo or with a team. 💰 $50,000 prize pool in $SURGE Token. ⚠️ Self-service hackathon This is a fully self-service hackathon. There are no live streams, kickoff sessions, or scheduled workshops. Participants can register, build, and submit at any time before the submission deadline.