HackStack

Project Info

GitLit

Devpost

Inspiration

We were inspired by how time consuming it is for developers to review code, check security, and test APIs across multiple tools. We wanted to create an all-in-one AI assistant that automatically analyzes any GitHub repo for code quality, design, and security while letting users test APIs in one place.

What it does

Our web app lets users log in with GitHub, fetch any repository, and automatically analyze it using Claude AI and CodeRabbit for code readability, security, errors, and system design. It then gives an overall score and provides an integrated Postman-style API tester all in one intuitive dashboard.

How we built it

We built our web app using Next.js and Node.js for the frontend and backend, designed the UI in Figma, and styled it with CSS for a clean, developer-friendly look. We integrated CodeRabbit to fetch GitHub code review comments, Claude AI to analyze readability, security, and system design, and Postman’s API tools to let users test endpoints directly within the app.

Challenges we ran into

We ran into challenges integrating with the CodeRabbit API, since it required a specific setup and authentication flow we didn’t initially know about. The CodeRabbit IP address also didn’t work at first we even reached out to their team on Slack and met them in person to troubleshoot the issue. We also struggled to retrieve the bearer token for Claude AI while making API calls, all while racing against time to get everything working before the deadline.

Accomplishments we're proud of

We’re proud of our teamwork, resilience, and collaboration throughout the hackathon. With the help of tools like Cursor and our determination to overcome every challenge, we managed to build a functional, AI-powered web app despite the technical hurdles and we’re proud of how far we’ve come as a team.

What we learned

We learned the importance of teamwork, grit, and perseverance how to work hard, stay positive, and have fun even under pressure. Most importantly, we learned to never give up and always believe in ourselves no matter how tough the challenges get.

What's next

Next, we plan to build a more complete and accurate grading system for analyzing codebases and improve the overall structure and UI to make the platform more engaging and user-friendly. We also aim to develop a structured database to track repo history and gather developer feedback and usage data to continuously improve GitLit into a smarter, more powerful AI development assistant.

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
  • Next.jsIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • JavaScriptClaimed
  • Node.jsClaimed

5 of 7 appear in the indexed code. 2 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

249 KB

Source files

49

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

0 stars