AI Code Review Tool

An intelligent code review tool powered by Mistral AI that provides comprehensive analysis of your code for security vulnerabilities, performance issues, and best practices.

Features

• 🤖 AI-Powered Analysis - Uses Mistral AI's latest models for intelligent code review
• 🔒 Security Focus - Identifies SQL injection, XSS, authentication issues, and more
• ⚡ Performance Review - Detects algorithmic complexity and optimization opportunities
• 📋 Best Practices - Ensures code quality, maintainability, and design patterns
• 🎯 Multiple Languages - Supports JavaScript, TypeScript, Python, Java, Go, Rust, and more
• 🎨 Clean UI - Modern, responsive interface built with Tailwind CSS
• 📊 Severity Levels - Issues categorized as Critical, High, Medium, or Low
• 💡 Actionable Suggestions - Each issue includes specific fix recommendations

Prerequisites

• Node.js 18+ installed
• A Mistral AI API key (get one at console.mistral.ai)

Quick Start

Option 1: Use Live Demo (Fastest)

Just visit: https://ai-code-review-tool-seven.vercel.app/

Option 2: Run Locally

1. Clone the repository

   git clone git@github.com:het-tale/ai-code-review-tool.git
   cd ai-code-review-tool

2. Install dependencies

   npm install

3. Set up environment variables

   Create a .env.local file in the root directory:

   MISTRAL_API_KEY=your_mistral_api_key_here

4. Run the development server

   npm run dev

5. Open your browser

   Navigate to http://localhost:3000

Usage

1. Paste Your Code - Copy and paste your code into the text area
2. Select Language - Choose the programming language from the dropdown
3. Choose Review Focus - Select what to focus on:
   • All - Comprehensive review (security + performance + best practices)
   • Security - Focus on vulnerabilities and security issues
   • Performance - Focus on optimization opportunities
   • Best Practices - Focus on code quality and maintainability
4. Click "Review Code" - Get your AI-powered analysis in seconds
5. Review Results - See issues categorized by severity with actionable suggestions

Quick Test

Click the "Load Sample" button to load example code with intentional issues for testing.

Project Structure

code-review-ai/
├── app/
│   ├── api/
│   │   └── review/
│   │       └── route.ts        # API endpoint for code review
│   ├── page.tsx                # Main page component
│   └── layout.tsx              # Root layout
├── components/
│   ├── CodeInput.tsx           # Code input form component
│   └── ReviewResults.tsx       # Results display component
├── lib/
│   └── mistral.ts              # Mistral AI client configuration
├── types/
│   └── index.ts                # TypeScript type definitions
├── .env.local                  # Environment variables (not in git)
└── README.md                   # This file

Tech Stack

• Framework: Next.js (App Router)
• Language: TypeScript
• AI Model: Mistral AI SDK
• Styling: Tailwind CSS
• Runtime: Node.js

API Response Format

The tool returns structured JSON with the following format:

{
  "summary": "Brief overall assessment",
  "issues": [
    {
      "severity": "critical" | "high" | "medium" | "low",
      "title": "Issue title",
      "description": "Detailed description",
      "lineNumber": 5,
      "suggestion": "How to fix it"
    }
  ],
  "strengths": ["Positive aspects"],
  "recommendations": ["General improvements"]
}

Development

Code Quality

The project uses:

• TypeScript for type safety
• ESLint for code linting

Acknowledgments

• Built with Mistral AI
• Powered by Next.js
• Styled with Tailwind CSS