Back
Explore EventsExplore ProjectsMy Projects
GitInterviewer — screenshot 1
GitInterviewer — screenshot 2
GitInterviewer — screenshot 3
GitInterviewer — screenshot 4

GitInterviewer

An Al-powered technical interviewer that crawls a candidate's GitHub profile to conduct adaptive, voice-enabled coding interviews and generates structured PDF scorecards.

Codex Community Hackathon - Pune

Links

Repository

github.com/kaverimeshram/GitInterviewer

Website

github.com/kaverimeshram/GitInterviewer

Demo video

youtu.be/y1f80qeeMd4?si=9jUs3ZfEvzMqkmis

Additional info

How was your experience building with Codex?

Building with Codex was a great experience. It helped me move much faster by generating boilerplate code, debugging issues, and suggesting implementation approaches. It allowed me to focus more on the product idea and user experience rather than getting stuck on repetitive coding tasks.

Describe your experience using Loops House as the hackathon platform. What worked well, what challenges (if any) did you face, and what improvements would you like to see?

Loops House provided a smooth experience for registration, project submission, and accessing event information. The platform was easy to navigate and helped keep everything organized. One improvement could be adding more real-time updates and clearer notifications for important deadlines and announcements.

Tell us about your overall experience at Codex Community Hackathon Pune.

My overall experience was excellent. I learned a lot about building AI-powered products, collaborating with developer tools, and turning ideas into working prototypes quickly. It was inspiring to see what other participants built and connect with people who share similar interests in technology and AI.

What could Codex Community improve to create a better experience for participants?

⁠The experience was already very good. Some additional mentor office hours, technical workshops, and networking opportunities could make it even more valuable. More guidance on project evaluation criteria and additional time for demos and feedback would also be helpful.

Team

1 member
  • KA

    Kaveri

    Owner

Overview

GitInterviewer is an AI-powered technical interview platform that creates personalized interviews from a candidate’s GitHub profile. The app analyzes public repositories, detects the candidate’s technologies and experience level, then runs an adaptive interview using a realtime voice AI agent. Candidates can answer by voice through a WebRTC-based OpenAI Realtime connection or switch to text input when needed. The platform generates interview questions based on the candidate’s actual projects, tracks the conversation, and produces a final evaluation report with scores for technical knowledge, problem solving, communication, confidence, strengths, weaknesses, and recommendations. Architecture Summary

ExploreProjectsMine