HackStack

Project Info

Rebase

Devpost

This project did not submit a demo video on Devpost.

Inspiration

Having worked with large codebases before, we know how overwhelming it can be to navigate and understand them—both for humans and AI. We wanted to create a low-token representation of a codebase that preserves its structure while making it easier to explore. Our goal was to fundamentally change how developers view and interact with code by introducing a hierarchical, AI-powered interface that abstracts away complexity and allows users to drill down only when necessary. We were also inspired by tools like Windsurf, which we love, and wanted to bring that intuitive experience to AI-powered code analysis.

What it does

Rebase is an AI-powered code analytics tool that helps developers quickly understand large codebases. It features: A tree-based file explorer for intuitive navigation AI-generated summaries and complexity analysis for files Code analytics, including lines of code, commits, and files changed AI-powered visualizations and diagrams to represent code structure GitHub integration for real-time insights

How we built it

We focused on designing an intuitive hierarchical interface that enables users to interact with code at different levels of abstraction. Our backend processes code efficiently, generating AI-powered summaries, complexity scores, and visualizations. We also worked on GitHub authentication and integrating real-time analytics into the dashboard.

Challenges we ran into

One of the biggest challenges was handling GitHub authentication—we were stuck on it for a while. Managing dependencies across files efficiently and optimizing AI context window usage were also tricky. Balancing performance with usability was another key challenge, especially when working with large codebases.

Accomplishments we're proud of

Successfully built a working prototype of our file tree explorer Implemented AI-generated summaries and complexity analysis Designed a scalable approach for integrating GitHub repositories Gained a deeper understanding of AI-driven software engineering

What we learned

Throughout this project, we learned a lot about: AI-driven software engineering and code analysis Managing dependencies across files in a structured way Efficiently utilizing the context window for AI-powered insights Overcoming authentication and API integration hurdles

What's next

This is just the beginning. Moving forward, Rebase can expand to integrate with popular AI software engineering services, provide deeper insights into code structure, and support more advanced AI-driven refactoring suggestions. Our goal is to make navigating and understanding large codebases effortless for developers everywhere.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • FlaskIn code
  • HTMLIn code
  • JavaScriptIn code
  • OpenAIIn code
  • PythonIn code
  • ReactIn code
  • Tailwind CSSIn code
  • PostgreSQLClaimed

8 of 9 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

81 KB

Source files

25

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars