Codium

Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

Codium AI: Revolutionizing Pull Request Reviews

Codium AI is at the forefront of transforming the way developers review pull requests with its suite of AI-powered tools. By leveraging advanced AI algorithms, Codium AI aims to streamline the pull request review process, providing developers with automated analysis, feedback, suggestions, and more. This technology empowers developers to code smarter, create more value, and boost confidence when pushing their code changes.

General
Author	Codium AI
Repository	https://github.com/Codium-ai/pr-agent
Type	AI-Powered Code Review abd Testing Tool

Start building with Codium AI

Visit the GitHub repository to explore and access all the Codium AI resources. Here, you can find code samples, documentation, and more to help you integrate Codium AI into your development workflow.

Codium Tutorials

Codium AI Resourses

Explore a wealth of Codium AI resources to enhance your pull request review process. These resources provide a great head start when revolutionizing your code review workflow.

Edit on GitHub

Codium AI technology page Hackathon projects

Discover innovative solutions crafted with Codium AI technology page, developed by our community members during our engaging hackathons.

AI Virtual Puppet Theater

AI Virtual Puppet Theater is an immersive AI powered browser experience that transforms users into live digital puppeteers through real time gesture control, facial tracking, and cinematic storytelling. The project combines computer vision, realtime animation, and interactive stage design to create a magical virtual theater where users control expressive 3D characters using natural human movements. Using webcam based hand tracking and facial detection, players can perform combat, emotional reactions, celebration animations, and cinematic interactions. The system tracks gestures, blinking, eye movement, facial expressions, and head motion to make puppet characters feel emotionally alive and deeply connected to the user. Characters react dynamically with expressive eyes, animated emotions, smooth movement interpolation, and theatrical body language. The platform includes a complete cinematic story mode featuring dramatic sequences between a King, Lion, Hero, and mysterious dark creature, brought to life through curtain transitions, realtime lighting, particle systems, and synchronized animation, all running directly inside the browser. The technical stack includes Next.js, TypeScript, Tailwind CSS, React Three Fiber, Three.js, Zustand, MediaPipe, TensorFlow.js, face-api.js, and Framer Motion, with strong focus on low latency interaction and immersive presentation quality.

Smart Port AI Operations Copilot

Smart Port AI Copilot is an intelligent operations system designed for modern port environments. It acts as a domain-specific AI assistant that helps port operators understand congestion, truck flow, emissions impact, and operational inefficiencies in real time. Unlike generic chatbots, Smart Port is scoped specifically for port logistics. It responds with structured, operational reasoning and focuses only on relevant port data and scenarios. The system can generate executive summaries, suggest operational actions, and simulate decision-making scenarios for improved throughput and reduced delays. The platform demonstrates how AI agents can be constrained to real-world industrial domains, making them safer, more reliable, and more useful in mission-critical environments like logistics infrastructure. Smart Port represents a step toward AI-driven ports that are faster, cleaner, and more efficient.

Bob the SAGE – AI Research Copilot

Bob the SAGE (Systematic Academic Guidance Engine) is an AI‑assisted research copilot that helps developers and researchers turn messy academic queries into structured insight. Given a topic like “CRISPR gene therapy”, it fetches real papers, builds a citation graph with PageRank to surface key work, constructs a timeline to highlight paradigm shifts, and then summarizes everything as a literature review and draft research proposal. Under the hood, SAGE is a full web app with a FastAPI backend and modern frontend. The citation graph and timeline engines have been hardened to handle noisy data, disconnected components, and edge cases, and the backend is covered by dozens of tests with 80%+ coverage. We used IBM Bob throughout the lifecycle: to review and improve the core algorithms, define five reusable Bob Skills (extraction, synthesis, graph analysis, translation, proposal), generate tests, produce a 600+ line security audit, and write architecture and API documentation. The app shows a clear pipeline from query to results and exposes controls for year range, language, and max papers, with sensible defaults and ethical API usage: no keys in the repo, pluggable data sources, and explicit respect for provider terms. For judges, Bob the SAGE is both a working demo you can run locally and a concrete example of how IBM Bob can accelerate building production‑style developer tools for research and education.

GitKit

GitKit is an AI-powered developer tool that helps engineering teams stay ahead of bugs before they happen. Instead of reacting to failures after the fact, GitKit proactively analyzes your entire GitHub repository and predicts which files carry the highest risk of breaking in the future. The core idea is simple but powerful: bugs don't appear randomly. Files that are frequently modified, lack test coverage, or sit at critical points in the codebase are far more likely to fail. GitKit surfaces exactly these files, ranked by a risk score from 0 to 100, so developers know where to focus their attention. IBM Bob was used as the primary development partner throughout the entire build. Bob's full repository context understanding helped generate the risk scoring logic, API routes, database schema, and UI components with remarkable speed and accuracy. Bob didn't just autocomplete code — it reasoned about the architecture, suggested improvements, and helped navigate complex Next.js app router patterns. The application is built with Next.js 14 using the app router, styled with Tailwind CSS, and stores all analysis results in Neon serverless PostgreSQL. Users simply paste a GitHub repository URL, and within seconds receive a beautiful heatmap dashboard showing every file color-coded by risk — red for high risk, yellow for medium, and green for safe. Each file card explains in plain English why it received its score — whether due to high commit churn, missing tests, or its position in a critical part of the codebase. This makes GitKit not just a detection tool but an educational one that helps developers write better, more resilient code over time.