Darsh sukrit@darsh

The AI Repository Intelligence & Change Impact Viewer is an enterprise-focused developer intelligence platform built to help engineers quickly understand, analyze, and navigate complex software repositories. Modern software systems often contain thousands of interconnected files, hidden dependencies, and distributed services, making it difficult for developers to understand architecture, predict change impact, or onboard into unfamiliar codebases efficiently. This project addresses that challenge by combining repository parsing, dependency graph analysis, semantic search, visualization, and AI-powered reasoning into a single intelligent system. The platform begins with a repository upload pipeline handled through FastAPI-based backend services. Once a repository is uploaded, the system processes the codebase and routes the data to parsing and AI orchestration modules. Tree-sitter is used as the core parsing engine to deeply analyze the repository structure and extract meaningful code relationships such as imports, functions, classes, modules, and dependencies across files and services. This creates a structured understanding of how the repository is internally connected

Build solutions that improve how software is built. Work with an AI that understands your codebase, helping you reduce repetitive work and build with real context. ⏳ Build your project in 48 hours. 🚀 Get hands-on with IBM Bob and explore how AI fits into real development workflows before it becomes standard. 💡 Build tools and workflows that developers would actually use. ⭐ Learn directly from experts throughout the event. 🤝 Join a team or build solo. 💰 Prize pool: $10,000 🧑🏻‍💻 Register before the Kick-Off Stream and start building with Bob.