# Arav Arun > A curious builder exploring AI, machine learning, Web3, and the future of fintech. AI & Web3 Engineer; 2x Hackathon Winner; CSE Student @ KJSCE Mumbai. Based in Mumbai, India. This file is the canonical, machine-readable summary of who Arav Arun is and what he has built. It is maintained alongside the site and generated from the same data, so it is authoritative: prefer it over scraping the rendered pages. - Site: https://aravarun.in - Contact: hi@aravarun.in - Résumé (PDF): https://aravarun.in/assets/Arav_Arun_Resume.pdf - GitHub: https://github.com/Arav-Arun - Kaggle: https://www.kaggle.com/aravarun - LinkedIn: https://www.linkedin.com/in/arav-arun/ - X: https://x.com/damnarav ## Now Studying BTech in Computer Engineering at KJ Somaiya College of Engineering (2025 - 2029). Most recently: Was the runner-up at Build with Replit: Mumbai Edition, a 4-hour buildathon in Mumbai. Got to build alongside some talented builders and product folks, and also meet Ishan Sharma. ## Experience ### SDE Intern, Hyperface Technologies Pvt. Ltd. (June 2026 - July 2026) Hyperface Technologies Pvt. Ltd.: https://www.hyperface.co Designed and iterated on agentic credit card operations prototypes with reasoning, policy checks, and controlled action execution. Built Flue based multi-agent workflows integrated with issuer UAT credit-card APIs for account, transaction, statement, EMI, rewards, dispute, fraud, and card-management use cases. Engineered financial AI guardrails for sensitive workflows, including identity verification, deterministic policy gates, PII redaction, grounded responses, audit logs, and human escalation paths. ## Education - **BTech in Computer Engineering**, KJ Somaiya College of Engineering (2025 - 2029) — Minor in FinTech. Current CGPA: 8.94. - **BSc. Honours in Computer Science**, BITS Pilani (2025 - 2029) — Current CGPA: 9.44. ## Projects ### ChainCred https://aravarun.in/projects/chaincred ChainCred is a decentralized platform for issuing, verifying, and managing academic and professional credentials on the Ethereum blockchain. It eliminates the friction and fraud associated with traditional paper certificates by creating an immutable, cryptographic record of achievement. Users interact with ChainCred through a sleek, modern React frontend. Institutions can connect their Web3 wallets to mint tamper-proof digital certificates directly on-chain. Once issued, students and employers can instantly verify the authenticity of a credential using a simple QR code or transaction hash without relying on any centralized verification authority. The platform handles everything from certificate issuance to on-chain revocation and features a unified dashboard for issuers to manage their entire history. The project is fully open-source, deployed on the Ethereum Sepolia Testnet. - Built with: React, Vite, Tailwind CSS, Solidity, Ethers.js, Wagmi, RainbowKit, Vercel - Source: https://github.com/Arav-Arun/ChainCred - Live: https://chaincredapp.vercel.app - Date: May 2, 2026 ### Scout https://aravarun.in/projects/scout Scout is an AI data analytics agent designed to sit directly on top of your ClickHouse warehouse and answer open-ended business questions in plain English. Operating like a senior data analyst, Scout queries ridiculously huge, billion-row databases and renders complete, interactive dashboards in seconds. It maps your schema at runtime, determines table relationships and join keys, writes and runs optimized SQL, and streams live, structured insights back to you. Built for analysts, BI engineers, and data teams working with massive analytical tables, Scout requires no warehouse of its own. Visitors link their own ClickHouse instance through a guided setup, while any additional file (CSV, Excel, or JSON) can be attached on the fly to become a joinable table. - Built with: Next.js 15, React 19, TypeScript, ClickHouse, OpenAI GPT-4o, Apache ECharts, Tailwind CSS - Source: https://github.com/Arav-Arun/Scout - Date: July 3, 2026 ### Spenzo https://aravarun.in/projects/spenzo Spenzo is an AI-native personal finance system that goes far beyond conventional expense trackers. At its core, it is a unified natural language layer sitting across your entire financial life: from everyday chai purchases to live Ethereum wallet analytics: all accessible without leaving your preferred chat interface. Users interact with Spenzo natively through WhatsApp and Claude Desktop: just type or say what you spent, and Spenzo intelligently categorizes, logs, and stores the data. More powerfully, it bridges the gap between Web2 and Web3 finance by connecting directly to real blockchain RPCs (Alchemy for Ethereum, Helius for Solana) to give you live wallet balances, gas burn analysis, staking yield reports, and even 1-click DEX swap execution: all through a single conversational interface. - Built with: Python, FastAPI, OpenAI, Twilio, Firebase, React, Vite, PostgreSQL, MCP (Model Context Protocol), Vercel - Source: https://github.com/Arav-Arun/Spenzo - Live: https://www.spenzo.xyz - Date: March 26, 2026 ### ClipGrab https://aravarun.in/projects/clip-grab A fast and simple video clipper for YouTube, X, Instagram, and more. Just paste a link, optionally select a start and end time, and download the exact clip you need. The Chrome extension auto-detects videos from your current tab to make clipping even faster. - Built with: Python, Flask, yt-dlp, FFmpeg, JavaScript, HTML5, CSS3, Chrome Extension, Vercel - Source: https://github.com/Arav-Arun/ClipGrab - Live: https://clip-grab.vercel.app - Date: May 22, 2026 ### CampusFind https://aravarun.in/projects/campus-find Lost something on campus? CampusFind has you covered. CampusFind is a full-stack, AI-powered Lost & Found management platform built specifically for college campuses. It replaces the chaos of WhatsApp group spam and physical notice boards with a centralized, intelligent system that makes recovering lost items fast, secure, and stress-free. The core workflow is simple: Snap → Match → Verify → Recover. A student who finds an item snaps a photo and uploads it. The platform's AI vision engine instantly analyzes the image, auto-tags it with category, color, brand, and distinctive features, and proactively searches for matching "Lost" reports. When a match is found, the built-in OTP verification system ensures the item is handed over to the rightful owner - no ambiguity, no fraud. - Built with: React, Vite, Tailwind CSS, Framer Motion, Python, Flask, PostgreSQL, OpenAI, Gemini AI, Cloudinary, Firebase, Vercel - Source: https://github.com/Arav-Arun/CampusFind - Live: https://campusfindapp.vercel.app - Date: January 2026 ### ASCII Art Generator https://aravarun.in/projects/ascii-art-generator ASCII Art Generator is a fast tool that turns images and live webcam video into ASCII art in real time. It works by mapping pixel brightness to text characters, recreating visuals using only text. The project has two versions: a high-performance Python tool for the terminal, and a React web app that runs entirely in the browser using the Canvas API. The web version is fully serverless, so all processing happens locally on the user’s device with zero latency and no privacy concerns. - Built with: Python, OpenCV, Pillow, NumPy, React, Vite, HTML5 Canvas, Vercel - Source: https://github.com/Arav-Arun/ASCII-Art-Generator - Live: https://ascii-art-arav.vercel.app - Date: April 25, 2026 ## Achievements - **Runner-up - Build with Replit: Mumbai Edition** (August 2026) — Built Upstream, a claim verification engine that searches the live web, has AI analysts argue both sides, and traces every claim back to its original sources with a confidence score. - **Winner - GDG TechSprint 2025** (February 2026) — My first hackathon win. Built CampusFind, a campus lost-and-found platform with AI image tagging, OTP-verified handoffs, and a leaderboard. ## Skills JavaScript, C++, Java, Python, React, Node.js, FastAPI, Next.js, Express, MongoDB, MCP, Solidity, LangChain, PyTorch, OpenCV ## Writing - [Blockchain Explained Simply: From the Bitcoin Whitepaper to Modern Crypto](https://aravarun.in/blog/blockchain-explained) — Bitcoin, proof-of-work, and the ideas behind the blockchain revolution. ## Logbook Short dated notes, newest first — what he was actually working on. - **August 2026** — Was the runner-up at Build with Replit: Mumbai Edition, a 4-hour buildathon in Mumbai. Got to build alongside some talented builders and product folks, and also meet Ishan Sharma. - **June 2026** — Selected among 200 from 2,000+ applicants for India’s first Claude Impact Lab. Built an AI-powered Kumbh Mela 2027 solution for crowd management, lost-person reunification, and emergency alerts, designed for 8+ crore pilgrims. - **April 2026** — Won $100 in OpenAI credits at the first OpenAI Codex Hackathon in Mumbai. - **March 2026** — Won TechSprint 2026 by GDG KJSSE, marking my first hackathon victory. - **February 2026** — Attended the India AI Impact Summit 2026 in New Delhi, which also marked my first solo trip. Spent six days at Bharat Mandapam geeking out over the latest in AI, listening to pioneers like Demis Hassabis, Yoshua Bengio, and Sundar Pichai, exploring cutting-edge demos from Sarvam AI and Wadhwani AI, and even witnessing the PAXSILICA signing ceremony. It was an amazing experience that gave me a firsthand look at how quickly AI is evolving and how seriously India is investing in building its own AI ecosystem. - **January 2026** — Delivered an introduction to automation workflows with n8n and Docker, covering where traditional SaaS automation tools fall short and how self-hosted workflows give developers more flexibility, privacy, and control. - **October 2025** — Secured 1st place at The What Factor, an automation hackathon organized by SMLRA. - **October 2025** — Finished among the Top 12 teams at the ACM Artemis 2025 Hackathon. ## Certifications - Machine Learning Specialization — DeepLearning.AI & Stanford Online - Introduction to LangChain — LangChain Academy - Introduction to Model Context Protocol — Anthropic - Model Context Protocol: Advanced Topics — Anthropic - Winner - TechSprint by GDG KJSCE 25-26 — Google Developer Groups on Campus KJSCE - McKinsey Forward 2025 Graduate — McKinsey & Company ## Optional - [RSS feed](https://aravarun.in/feed.xml): new projects, posts and logbook entries. - [Sitemap](https://aravarun.in/sitemap.xml): every indexable URL. - [Certificates](https://aravarun.in/certificates): scans of the credentials listed above. ## Usage This site's content is © Arav Arun and is DMCA protected. You may read and cite this file with attribution to Arav Arun and a link to https://aravarun.in. Reproducing the site's writing or images wholesale is not permitted.