Bakar MD@muhammad_abubakar

It is the clone of a product hunting website made in MERN STACK, GraphQL and Tailwind CSS. A responsive UI and user data is transferred through GraphQL. React Redux is used for state management. JWT tokens are used for authentication and authorization.

Qubic OmniVault is a comprehensive digital asset management platform designed to securely store, organize, and share digital files and assets across personal and enterprise environments. It leverages AI-powered categorization, smart tagging, and intelligent search to make finding and managing files seamless. Users can collaborate in real-time, set granular access permissions, and track version histories. The platform supports cloud synchronization, end-to-end encryption, and integrates with popular third-party services like Google Drive, Dropbox, and Slack. OmniVault provides dashboards, analytics, and automation tools to streamline workflows, making digital asset management efficient, secure, and user-friendly for teams of any size.

CUDI SafePay is a decentralized, private micropayment system designed to empower creators, journalists, and NGOs, enabling them to receive direct support from their audiences without intermediaries or censorship. Our goal is to make digital finance globally accessible and eliminate the barriers of traditional platforms that impose high fees (2.9%–3.4%) and compromise privacy. At the heart of CUDI is Bulut, an Artificial Intelligence (AI) agent that transforms the complexity of the blockchain into a simple, conversational experience. Using the AI/ML API, Bulut translates natural language commands ("Pay 15 USDC to @FreeJournalist") into structured blockchain instructions (JSON). Execution takes place on the Arc Blockchain, with USDC as the native gas. Thanks to integration with the Circle Developer-Controlled Wallets SDK and its Paymaster feature, we guarantee gas-free transactions for the end user. Furthermore, adoption is simplified by eliminating the need for seed phrases and managing access via PIN and biometrics. CUDI SafePay offers the first smart, censorship-resistant, and frictionless payment solution

LeetCode Agent – A Smart Coding Companion LeetCode Agent is an intelligent assistant designed to make competitive programming practice on LeetCode more structured, personalized, and automated. Many programmers struggle with consistency, deciding which problems to solve, and managing their GitHub repositories where they maintain their solutions. This project aims to solve those pain points by functioning as a daily practice companion, an automation tool, and a progress tracker. Purpose and Vision The primary goal of LeetCode Agent is to help programmers at all levels practice efficiently while staying motivated. Beginners often lack structure, intermediate users seek consistency and better tracking, and advanced users want smart recommendations and automation. LeetCode Agent caters to all three classes by analyzing past progress, recommending balanced problems, keeping repositories neat, and sending reminders that spark curiosity. The vision is to create an agent-like experience—something that works in the background so the user can focus only on problem-solving. Core Features Daily Problem Recommendation Each day, the system suggests a problem tailored to the user’s journey. It does this by analyzing the GitHub repository, tracking which categories and difficulties have already been solved, and then selecting a problem that balances progress. If the user wants more practice, alternative suggestions are also provided. Future versions may include AI-enhanced recommendations using embeddings and historical solution patterns to predict the “next best problem” based on what others solved after similar progress. Repository Analysis The agent automatically inspects the structure of the user’s GitHub repository. Many programmers organize their solutions by categories such as Arrays/, Backtracking/, or DynamicProgramming/. The agent parses this structure, identifies unsolved or underrepresented topics, and

One of the biggest challenges in modern research is dealing with information overload. Analysts, researchers, and organizations often need to process vast amounts of unstructured data—ranging from academic papers and PDFs to dynamic web content. Manually filtering, extracting, and validating insights is time-consuming, prone to bias, and difficult to scale. Our project addresses this gap by building a mini AI research lab, a system that combines retrieval, structured extraction, experimentation, and judgment. At its core, we use GPT-5 efficiently as a multi-role reasoning agent rather than just a conversational assistant. For example, GPT-5 powers the Extractor, transforming raw text into structured evidence with minimal noise. The Experimenter module leverages GPT-5 to simulate hypotheses, cross-check facts, and test consistency across different sources. Finally, the Judge role allows GPT-5 to evaluate credibility, logical soundness, and contextual relevance—acting as a safeguard against misinformation. By integrating GPT-5 with hybrid retrieval (FAISS + BM25), we ensure precise context delivery while minimizing token usage. This efficient workflow solves a real-world problem: enabling faster, more reliable, and scalable knowledge discovery.

Introducing Chat Market: Revolutionizing Buying and Selling with AI-Powered Conversations The Problem: We've all been there - cluttered homes, unused items, and a mental wishlist of things we want to buy but never get around to searching for. The traditional buying and selling process is time-consuming and tedious, involving hours of listing items, taking photos, writing descriptions, and deciding prices. The Solution: Enter Chat Market, a game-changing platform that harnesses the power of agentic AI to make buying and selling a breeze. Our platform allows users to buy and sell at lightning speed, with no more tedious listing or searching required. Simply have a brief chat with our AI agent, and it'll take care of the legwork for you. How it Works: Buy: Create and update your wishlist with our chat interface, and our AI agent will give you feedback, search for available products, and advise whether to buy now or wait. Sell: Upload a photo of your item, and our AI will infer what it is, create a listing, and suggest a price based on comparable items. You can modify the listing, and our AI will even offer tips on how to market your item better. Target Market: We're initially targeting individual users, but businesses can also benefit from our platform. Business Model: Chat Market is free to use, with a small commission on transactions made through our platform. We may also introduce a premium subscription model for advanced features, such as autonomous item selling and shopping agents. What Sets Us Apart: Our chat-based interface, powered by AI, makes buying and selling faster, easier, and more enjoyable. Say goodbye to tedious listing and searching, and hello to a seamless, conversational experience.

I have developed a sophisticated blog post generator that automates the creation of high-quality blog content by fetching information from specified URLs. This innovative tool leverages advanced technologies and integrations to streamline the content creation process. Here’s an overview of the system: Blog Post Generator Overview Functionality: The blog post generator automates the creation of blog posts by fetching information from specified URLs, processing the data, and generating coherent and engaging blog content. Technologies Used: Langflow: Purpose: Core framework managing workflow of data retrieval and processing. Function: Orchestrates information flow from input URLs to final blog output. LLaMA3 (through Groq API): Purpose: Advanced language processing model. Function: Processes retrieved information to generate well-structured, relevant blog posts. The Groq API ensures seamless integration and efficient use of LLaMA3’s capabilities. Streamlit: Purpose: Provides the frontend interface. Function: Offers an intuitive interface for users to input URLs, initiate blog generation, and view the generated content. Ensures a smooth user experience. How It Works: Input URLs: Users provide URLs with the desired information for blog posts. Data Retrieval: Langflow efficiently extracts data from these URLs. Content Generation: The extracted information is processed by the LLaMA3 model via the Groq API, generating high-quality blog content. Output: The generated blog post is displayed on the Streamlit interface for review and editing. Benefits: Efficiency: Automates content creation, reducing time and effort. Quality: Utilizes advanced language models for coherent, engaging content. User-Friendly: Intuitive interface accessible to users with varying technical expertise. This blog post generator is a powerful tool for content creators, marketers, and businesses to enhance their content production capabilities with minimal effort.

Paperia Overview: Paperia is a tool designed to digitize printed and handwritten documents (invoices, receipts, purchase orders, etc.) and integrate them into a record-keeping system. It automates the storage and organization of documents, linking them with other business software systems. Paperia provides standard and customizable reports, utilizes data analysis, charts, and dashboards to offer valuable business insights. Key Benefits: Efficiency: Reduces manual effort in document management. Accuracy: Minimizes errors through automation. Compliance: Helps maintain regulatory compliance. Decision-Making: Provides actionable insights for strategic decisions. Frontend: html,boostrap, jquery Backend:Flask and MySQLL). OCR and Data Extraction: Implement OCR (Optical Character Recognition) for digitizing printed and handwritten documents easyOCR. Integration: Ensure the system can integrate with other business software via APIs.

Teams work together with multiple AI agents in shared workspaces to design, build, and launch complete AI products — from initial idea to market-ready app. 📅 February 23– March 1, 2026 ⏱️ 6 days to build and ship an end-to-end agentic AI product 🤝 Work together in shared AI workspaces where your team and AI agents collaborate in real time 🔧 Build with multiple AI agents that handle development, design, testing, and documentation together 🎯 Create everything in one place — from ideation to product to marketing materials, all by prompting and observing 🚀 Focus on real-world products that teams could actually ship and use 🏆 $3,500 in prizes + premium 3-month Complete.dev access for top teams 🧑‍💻 Join your team workspace and start building together

Join Deriv and lablab.ai for a high-intensity hybrid hackathon where top builders create AI prototypes, demo their work, and get fast-tracked to interviews. When • Sat, Jan 31, 2026- On-Site Pre-Hackathon: Deriv AI Meetup (Dubai) • Fri, Feb 6 - Opening words, Challenge, and Hackathon kick-off. (Dubai) • Sat, Feb 7 - Build and ship your prototype - 12 hours (Onsite +Online) • Sun, Feb 8 - Demos, judging, and next steps for standout teams. (Onsite +Online) On-Site Pre-Hackathon: Deriv AI Meetup Sat, Jan 31, 2026 · 2:00–6:00 PM (GST) · Dubai In-person talks, workshops, team formation, and networking with the Deriv team. 👉 Deriv AI Meetup registration What's in it for you • USD $10,000+ in prizes across categories • Mentors available to unblock you when you're stuck • Fast-track interviews for top performers - skip the queue • Real problems to solve - not toy demos Format • Teams of 1-3 • Hybrid: Dubai on-site or fully remote • On-site spots confirmed after screening Location • One by Omniyat, 24th Floor, Al Mustaqbal Street, Business Bay, Dubai, UAE • Travel and accommodation not provided. Apply now • Spots are limited. Shortlisting begins right after the event.

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 $40,000 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 $50,000 in USDC & 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!