16
12
Viet Nam
2+ years of experience
Hi, my name is Akashi (あかし) . I am currently App - Cloud team leader at R&D Digital center - RALACO and Director of AI & Software Development in Edtech Hub Uganda. With the aim of being a Fullstack developer, I enjoy spending my time learning Front-end technology with projects on Web APP (reactjs, angular) and Mobile APP (flutter, react native) , along with thriving in the field of AI, Machine Learning . I am also a starter self-taught backend developer (with Nodejs , Flask & Spring Boot as my current frameworks) You can contact with me via Facebook https://www.facebook.com/profile.php?id=100008450770058

Problem Statement: Weather often disturbs daily plans, events, and travel. Many People and organizations donot have any easy way to get real-time, personalized weather guidance. Solution: ClimeAI solves this Problem and Provide an AI powered weather assistant that combines real-time weather data with smart advice for event planning, travel guidance, and safety decisions. It understands the user queries and keep the context through chat memory, deliver recommendations such as best travel times, event safety plans, and packing suggestions. Technology Stack: The platform built using FastAPI (Python), LangGraph, MongoDB, and Docker, with APIs including OpenWeatherMap, OpenCageData, AIML API, Mistral API Key, and Eleven Labs for smart intelligence, orchestration, and natural voice. Value: ClimeAI help users and businesses to make smarter, safer, and faster weather-aware decisions, save time, reduce risks, and improving their planning efficiency.
21 Sep 2025

HealthBridge is an intelligent healthtech platform designed to revolutionize access to medical consultations. It allows certified doctors from around the world to create detailed profiles showcasing their specializations, availability, pricing, and certifications. Patients can search for doctors based on symptoms and location, and consult with them either virtually or in-person. Leveraging LLaMA for symptom understanding, multilingual translation, and patient-doctor interaction, and Groq for real-time AI inference, HealthBridge ensures lightning-fast and accurate responses. Features include AI symptom checkers, doctor filtering by budget and expertise, secure video consultations, and voice/text accessibility. It's a bridge between care and convenience for patients globally.
8 Jul 2025

GitGuard AI is a security-focused plugin for Trae IDE designed to protect developers and businesses from costly data breaches. It scans code as you type, instantly flagging secrets like API keys, database passwords, and cryptocurrency wallet mnemonics with red highlights. The tool suggests secure alternatives (e.g., environment variables) and logs findings for compliance. The plugin leverages: Multi-layer pattern matching (regex + NLP) to detect 50+ secret types including AWS keys, database credentials, and cryptocurrency mnemonics Novita.ai's LLMs for contextual analysis that reduces false positives by 72% compared to basic scanners Zilliz vector database for storing and retrieving secret patterns with millisecond latency Real-time code analysis that scans every keystroke without impacting IDE performance
15 Jun 2025

KONEKTA is an AI-driven digital connectivity platform designed to optimize resource allocation, enhance bandwidth efficiency, and provide smart knowledge discovery for underserved communities. 🔹 AI-Powered Smart Matching: NLP-driven recommendations connect educators, healthcare workers, and policymakers with the right resources and expertise. 🔹 Low-Bandwidth Optimization: Uses edge caching, PWA support, and lightweight AI models to enable offline-first access in poorly connected areas. 🔹 Energy-Efficient Network AI: Dynamically optimizes power consumption and bandwidth allocation, ensuring sustainable connectivity. 🔹 Public Sector Scalability: Enables schools, hospitals, and government institutions to deploy AI-powered digital services efficiently. KONEKTA’s real-time heatmaps and AI-driven analytics help visualize network utilization, ensuring seamless digital service delivery, even in constrained environments. 🚀
2 Mar 2025

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. 🚀
16 Feb 2025

In the vast expanse of space, where every resource is precious and every decision critical, a new AI-powered system is revolutionizing how we manage space mission resources. This innovative project brings together a crew of specialized AI agents, each designed to handle specific aspects of space resource management, from real-time monitoring to strategic planning. At the heart of this system lies a sophisticated collaboration between five distinct AI agents, working in harmony to ensure optimal resource utilization in space missions. The Database Agent maintains constant vigilance over resource levels and consumption patterns, while a Research Specialist, powered by Serper API, scours the internet for relevant insights and solutions to detected anomalies. These agents work alongside a Mission Integration Strategist that predicts future resource requirements, a Resource Management Specialist that develops dynamic allocation strategies, and a Reporting Analyst that transforms complex data into actionable intelligence. What sets this system apart is its ability to not just monitor resources, but to actively predict and prevent potential shortages before they occur. Built using the CrewAI framework, the system demonstrates the power of collaborative AI in solving complex real-world challenges. By integrating external tools like Serper for real-time research capabilities, the agents can access the latest information and best practices in space resource management, ensuring decisions are always made with the most current data available. In space operations, where resource management isn't just about efficiency but survival, this system represents a new paradigm in mission support. Through real-time monitoring, predictive analytics, and adaptive resource allocation strategies, this AI crew works tirelessly to support humanity's greatest adventures beyond Earth.
9 Feb 2025

The long-term vision for LibAI is to create an adaptable, AI-powered platform that revolutionizes content management and user interaction. Built with Next.js, Supabase, ShadCN, and Tailwind CSS, LibAI emphasizes efficient user management, dynamic content delivery, and seamless adaptability based on internet speed. The platform will incorporate Retrieval-Augmented Generation (RAG)-based query capabilities, allowing users to access relevant, AI-generated responses from vast datasets. Additionally, LibAI will support collaborative features like note sharing among students, enhancing the educational experience. The platform will also include intelligent filtering systems to detect and remove unwanted, negative, or harmful material, ensuring a safe and positive learning environment. The project’s ultimate goal is to integrate personalized, AI-driven content recommendations, expand external API integrations, and provide robust collaboration tools for educational institutions and organizations. LibAI aims to bridge the digital divide, offering equitable access to resources and fostering an innovative, collaborative, and secure learning space for schools and communities.
26 Jan 2025

Aslan AI relapse prevention in healthcare, particularly in mental health and addiction recovery. Many individuals struggle with emotional crises and lack accessible, immediate support during these vulnerable moments. To address this, Aslan offers an innovative AI-driven solution that provides real-time emotional support, helping users navigate challenging moments and prevent relapse. Aslan engages users in conversational, nonjudgmental interactions, dynamically adjusting its responses to validate emotions, identify underlying needs, and offer personalized interventions. The system is designed to help users express their emotions freely, offering them a safe space for self-reflection and growth. Aslan helps users develop a deeper understanding of their feelings and take actionable steps toward emotional well-being. Key functionalities include journaling prompts, mindfulness exercises, and value-driven decision-making tools that empower users to cope with stress and regain control during difficult times. The AI also features an adaptive response mechanism, which determines the best approach, whether to suggest an intervention first or help the user clarify their emotions and needs. A standout feature is the rant-friendly space, where users can vent freely, with built-in flagging mechanisms to detect concerning content based on varying threat levels (white, yellow, orange, red). This ensures that users in crisis are promptly directed to appropriate resources, such as crisis hotlines or clinical professionals. The primary target audience for Aslan includes individuals in recovery from addiction, those dealing with mental health issues, and anyone who needs ongoing emotional support. By offering real-time interventions and a supportive environment, Aslan reduces the risk of relapse and creates long-term emotional resilience.
11 Dec 2024

Lakidogs is an innovative project that leverages NFTs and cryptocurrency to create a self-sustaining ecosystem for rescued dogs. Each dog is represented by a unique NFT, which not only serves as a digital asset but also ties directly to the animal’s well-being. Through this system, dogs can ‘work’ by performing tasks such as security, therapy, or companionship, generating income that sustains their care. The platform’s economy is powered by Lakicoin, a cryptocurrency used for transactions. Lakidogs aims to reduce animal abandonment while providing economic opportunities for humans, creating a virtuous cycle of social impact.
1 Dec 2024