XCodeReviewer - Your Intelligent Code Audit Partner 🚀

XCodeReviewer is a modern code audit platform powered by Large Language Models (LLM), designed to provide developers with intelligent, comprehensive, and in-depth code quality analysis and review services.

No deployment needed, access the online demo directly (data stored locally in browser, all core features supported):

https://xcodereviewer-preview.vercel.app

In the fast-paced world of software development, ensuring code quality is crucial. Traditional code audit tools are rigid and inefficient, while manual audits are time-consuming and labor-intensive. XCodeReviewer leverages the powerful capabilities of LLM to revolutionize the way code reviews are conducted:

• 🤖 AI-Driven Deep Analysis: Beyond traditional static analysis, understands code intent and discovers deep logical issues.
• 🎯 Multi-dimensional, Comprehensive Assessment: From security, performance, maintainability to code style, providing 360-degree quality evaluation.
• 💡 Clear, Actionable Fix Suggestions: Innovative What-Why-How approach that not only tells you "what" the problem is, but also explains "why" and provides "how to fix" with specific code examples.
• ✅ Multi-Platform LLM/Local Model Support: Implemented API calling functionality for 10+ mainstream platforms (Gemini, OpenAI, Claude, Qwen, DeepSeek, Zhipu AI, Kimi, ERNIE, MiniMax, Doubao, Ollama Local Models), with support for free configuration and switching
• ⚙️ Visual Runtime Configuration: Configure all LLM parameters and API Keys directly in the browser without rebuilding images. Supports API relay services, with configurations saved locally in the browser for security and convenience.
• ✨ Modern, Beautiful User Interface: Built with React + TypeScript, providing a smooth and intuitive user experience.

Real-time display of project statistics, quality trends, and system performance, providing comprehensive code audit overview

Support for quick code snippet analysis with detailed What-Why-How explanations and fix suggestions

Integrated GitHub/GitLab repositories, supporting multi-language project audits and batch code analysis

Perfect for quick deployment and testing without a server, with global CDN acceleration.

Click the button below to deploy directly to Vercel:

# 1. Install Vercel CLI
npm i -g vercel

# 2. Login to Vercel
vercel login

# 3. Deploy project
vercel

# 4. Deploy to production
vercel --prod

1. Visit Vercel Dashboard
2. Click "Add New..." → "Project"
3. Import your GitHub repository
4. Vercel will automatically detect Vite project configuration
5. Configure environment variables (minimum required):

   VITE_LLM_PROVIDER=your_llm_provider
   VITE_LLM_API_KEY=your_api_key_here
   VITE_USE_LOCAL_DB=true
   

6. Click "Deploy"

✨ Vercel Deployment Advantages:

• ✅ Global CDN acceleration for fast access
• ✅ Automatic HTTPS and domain configuration
• ✅ Zero configuration, ready to use
• ✅ Custom domain support
• ✅ Automatic deployment (auto-update on Git push)

✨ Database Mode:

• Automatically uses local database mode (IndexedDB) by default, data stored in browser
• No database configuration needed, ready to use out of the box
• To use Supabase cloud database, configure environment variables

⚠️ Important Notes:

• Vercel is primarily for frontend deployment; backend APIs need separate deployment
• After deployment, configure runtime settings at /admin page

Directly use the latest published Docker image, supports x86, ARM64 (Mac M-series), and ARMv7 architectures:

# 1. Pull the latest image
docker pull ghcr.io/lintsinghua/xcodereviewer:latest

# 2. Run container
docker run -d \
  -p 8888:80 \
  --name xcodereviewer \
  --restart unless-stopped \
  ghcr.io/lintsinghua/xcodereviewer:latest

# 3. Access the application
# Open http://localhost:8888 in your browser

Use specific version:

# Pull specific version (e.g., v1.1.0)
docker pull ghcr.io/lintsinghua/xcodereviewer:v1.1.0

# Run
docker run -d -p 8888:80 --name xcodereviewer ghcr.io/lintsinghua/xcodereviewer:v1.1.0

If you need custom build:

# 1. Clone the project
git clone https://github.com/lintsinghua/XCodeReviewer.git
cd XCodeReviewer

# 2. Build and start with Docker Compose
docker-compose up -d

# 3. Access the application
# Open http://localhost:8888 in your browser

✨ Runtime Configuration (Recommended)

After Docker deployment, you can configure all settings directly in the browser without rebuilding the image:

1. Visit http://localhost:8888/admin (System Management page)
2. Configure LLM API Keys and other parameters in the "System Configuration" tab
3. Click save and refresh the page to use

📖 For detailed configuration instructions, see: System Configuration Guide

Suitable for development or custom modifications.

• Node.js 18+
• pnpm 8+ (recommended) or npm/yarn

# 1. Clone the project
git clone https://github.com/lintsinghua/XCodeReviewer.git
cd XCodeReviewer

# 2. Install dependencies
pnpm install  # or npm install / yarn install

# 3. Configure environment variables
cp .env.example .env
# Edit .env file, configure required parameters (see configuration guide below)

# 4. Start development server
pnpm dev

# 5. Access the application
# Open http://localhost:5173 in your browser

Edit .env file and configure the following required parameters:

# ========== Required Configuration ==========
# LLM Provider (gemini|openai|claude|qwen|deepseek|zhipu|moonshot|baidu|minimax|doubao|ollama)
VITE_LLM_PROVIDER=gemini
# Corresponding API Key
VITE_LLM_API_KEY=your_api_key_here

# ========== Database Configuration (Choose One) ==========
# Option 1: Local Database (Recommended, ready to use)
VITE_USE_LOCAL_DB=true

# Option 2: Supabase Cloud Database (Multi-device sync)
# VITE_SUPABASE_URL=https://your-project.supabase.co
# VITE_SUPABASE_ANON_KEY=your_anon_key

# Option 3: Demo Mode (No database, data not persistent)

# ========== Optional Configuration ==========
# GitHub Integration (for repository analysis)
# VITE_GITHUB_TOKEN=your_github_token

# Output Language (zh-CN: Chinese | en-US: English)
VITE_OUTPUT_LANGUAGE=en-US

# Analysis Parameters
VITE_MAX_ANALYZE_FILES=40    # Max files per analysis
VITE_LLM_CONCURRENCY=2       # Concurrent requests
VITE_LLM_GAP_MS=500          # Request interval (ms)

For timeout or connection issues, adjust these parameters:

VITE_LLM_TIMEOUT=300000                      # Increase timeout
VITE_LLM_BASE_URL=https://your-proxy.com/v1 # Use proxy or relay service
VITE_LLM_CONCURRENCY=1                       # Reduce concurrency
VITE_LLM_GAP_MS=1000                         # Increase request interval

Custom Headers Example (for special relay services):

# JSON format string
VITE_LLM_CUSTOM_HEADERS='{"X-API-Version":"v1","X-Custom-Auth":"token123"}'

# Switch to OpenAI
VITE_LLM_PROVIDER=openai
VITE_OPENAI_API_KEY=your_key

# Switch to Qwen
VITE_LLM_PROVIDER=qwen
VITE_QWEN_API_KEY=your_key

VITE_USE_LOCAL_DB=true

VITE_SUPABASE_URL=https://your-project.supabase.co
VITE_SUPABASE_ANON_KEY=your_key

# 1. Install Ollama
curl -fsSL https://ollama.com/install.sh | sh  # macOS/Linux
# Windows: Visit https://ollama.com/download

# 2. Pull model
ollama pull llama3  # or codellama, qwen2.5, deepseek-coder

# 3. Configure XCodeReviewer
# In .env:
VITE_LLM_PROVIDER=ollama
VITE_LLM_MODEL=llama3
VITE_LLM_BASE_URL=http://localhost:11434/v1

VITE_LLM_PROVIDER=baidu
VITE_BAIDU_API_KEY=your_api_key:your_secret_key

VITE_OUTPUT_LANGUAGE=zh-CN  # Chinese (default)
VITE_OUTPUT_LANGUAGE=en-US  # English

VITE_LLM_PROVIDER=gemini  # Currently active platform

# Pre-configure all platforms
VITE_GEMINI_API_KEY=key1
VITE_OPENAI_API_KEY=key2
VITE_QWEN_API_KEY=key3

import { logger, LogCategory } from '@/shared/utils/logger';

// Log user actions
logger.logUserAction('Create Project', { projectName, projectType });
logger.logUserAction('Start Audit', { taskId, fileCount });

XCodeReviewer supports 10+ mainstream LLM platforms, choose freely based on your needs:

# Universal configuration (recommended)
VITE_LLM_PROVIDER=gemini
VITE_LLM_API_KEY=your_api_key_here

# Or use platform-specific configuration
VITE_GEMINI_API_KEY=your_gemini_key
VITE_OPENAI_API_KEY=your_openai_key
# ... More platforms in .env.example

For cloud data sync:

1. Visit Supabase to create a project
2. Get URL and anonymous key
3. Execute supabase/migrations/full_schema.sql in Supabase SQL Editor
4. Configure in .env

XCodeReviewer/
├── src/
│   ├── app/                # Application configuration
│   │   ├── App.tsx         # Main application component
│   │   ├── main.tsx        # Application entry point
│   │   └── routes.tsx      # Route configuration
│   ├── components/         # React components
│   │   ├── layout/         # Layout components (Header, Footer, PageMeta)
│   │   ├── ui/             # UI component library (based on Radix UI)
│   │   ├── system/         # System configuration components
│   │   ├── database/       # Database management components
│   │   └── debug/          # Debug components
│   ├── pages/              # Page components
│   │   ├── Dashboard.tsx   # Dashboard
│   │   ├── Projects.tsx    # Project management
│   │   ├── InstantAnalysis.tsx # Instant analysis
│   │   ├── AuditTasks.tsx  # Audit tasks
│   │   └── AdminDashboard.tsx # System management
│   ├── features/           # Feature modules
│   │   ├── analysis/       # Analysis related services
│   │   │   └── services/   # AI code analysis engine
│   │   └── projects/       # Project related services
│   │       └── services/   # Repository scanning, ZIP file scanning
│   ├── shared/             # Shared utilities
│   │   ├── config/         # Configuration files
│   │   │   ├── database.ts      # Unified database interface
│   │   │   ├── localDatabase.ts # IndexedDB implementation
│   │   │   └── env.ts           # Environment variable configuration
│   │   ├── types/          # TypeScript type definitions
│   │   ├── hooks/          # Custom React Hooks
│   │   ├── utils/          # Utility functions
│   │   │   └── initLocalDB.ts   # Local database initialization
│   │   └── constants/      # Constants definition
│   └── assets/             # Static assets
│       └── styles/         # Style files
├── supabase/
│   └── migrations/         # Database migration files
├── public/
│   └── images/             # Image resources
├── scripts/                # Build and setup scripts
└── rules/                  # Code rules configuration

Visit /admin System Management page and configure in the "System Configuration" tab:

• Select the LLM platform you want to use (Gemini, OpenAI, Claude, etc.)
• Enter API Key (supports universal Key or platform-specific Key)
• Optional: Configure model name, API base URL (for relay services)

• Enter relay service address in "API Base URL" (e.g., https://your-proxy.com/v1)
• Enter the API Key provided by the relay service
• Save configuration

• Max analyze files, concurrent requests, request interval
• Output language (Chinese/English)

After configuration, click "Save All Changes" and refresh the page to use.

1. Visit the /instant-analysis page
2. Select programming language (supports 10+ languages)
3. Paste code or upload file
4. Click "Start Analysis" to get AI analysis results
5. View detailed issue reports and fix suggestions

1. Visit the /projects page
2. Click "New Project" to create a project
3. Configure repository URL and scan parameters
4. Start code audit task
5. View audit results and issue statistics

1. Create audit tasks in project detail page
2. Select scan branch and exclusion patterns
3. Configure analysis depth and scope
4. Monitor task execution status
5. View detailed issue reports

1. Click the "Export Report" button on the task detail page
2. Choose export format:
   • JSON Format: Structured data, suitable for programmatic processing and integration
   • PDF Format: Professional report, suitable for printing and sharing (via browser print function)
3. JSON reports contain complete task information, issue details, and statistical data
4. PDF reports provide beautiful visual presentation with full Chinese character support
5. Report contents include: project information, audit statistics, issue details (categorized by severity), fix suggestions, etc.

PDF Export Tips:

• After clicking "Export PDF", the browser print dialog will appear
• It's recommended to uncheck the "Headers and footers" option in print settings for a cleaner report (to avoid displaying URLs and other information)
• Select "Save as PDF" in the print dialog to save the report file

# Development mode
pnpm dev

# Build production version
pnpm build

# Preview build results
pnpm preview

# Code linting
pnpm lint

💡 API Format Support: XCodeReviewer supports 3 mainstream API formats:

• OpenAI-Compatible Format (Most Common): Works with most relay services and OpenRouter
• Gemini Format: Google Gemini official and compatible services
• Claude Format: Anthropic Claude official and compatible services

Simply select the corresponding LLM provider, enter the relay service address and Key. The custom headers feature can meet additional requirements of special relay services.

💡 Note: Without Supabase config, system runs in demo mode without data persistence

We warmly welcome all forms of contributions! Whether it's submitting issues, creating PRs, or improving documentation, every contribution is important to us. Please contact us for detailed information.

1. Fork this project
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Create a Pull Request

• React & Vite: Modern frontend development experience
• TypeScript: Type safety guarantee
• Tailwind CSS: Modern CSS framework
• Radix UI: Accessible UI component library

• Google Gemini AI: Powerful AI analysis capabilities
• OpenAI: GPT series models support
• Anthropic Claude: Claude models support
• DeepSeek: Domestic AI model support
• Alibaba Qwen: Enterprise AI service
• Zhipu AI: GLM series models
• Moonshot AI: Kimi model support
• Ollama: Local model deployment solution

• Supabase: Convenient backend-as-a-service support
• IndexedDB: Browser local storage solution

• Recharts: Professional chart components
• Lucide Icons: Beautiful icon library
• Sonner: Elegant notification component
• fflate: ZIP file processing

• Thanks to all contributors who submitted Issues and Pull Requests
• Thanks to all developers who starred this project
• Thanks to the open source community for their selfless sharing
• And all the authors of open source software used in this project!

Thanks to these amazing contributors who make XCodeReviewer better!

• Project Link: https://github.com/lintsinghua/XCodeReviewer
• Issue Reports: Issues
• Author Email: lintsinghua@qq.com

Currently, XCodeReviewer is in rapid prototype validation stage. Based on project development and community feedback, our roadmap includes:

• ✅ Multi-Platform LLM Support: Implemented API integration for 10+ mainstream platforms (Gemini, OpenAI, Claude, Qwen, DeepSeek, Zhipu AI, Kimi, ERNIE, MiniMax, Doubao, Ollama), with flexible configuration and switching
• ✅ Local Model Support: Added Ollama local model integration to meet data privacy requirements
• ✅ Visual Configuration Management: Implemented runtime configuration system supporting browser-based configuration of all LLM parameters and API Keys, API relay service support, no need to rebuild images
• ✅ Universal Relay Service Support: All LLM platforms support API relay services, self-hosted instances, and OpenRouter, with custom headers support, covering 99.9% of use cases
• ✅ Professional Report Generation: Generate professional audit reports in various formats based on different needs, with customizable templates and format configurations
• 🚧 CI/CD Integration & PR Auto-Review: Plan to implement GitHub/GitLab CI integration, supporting automatic PR-triggered reviews, intelligent comments, quality gates, incremental analysis, and complete code review workflows
• Multi-Agent Collaboration: Introduce multi-agent architecture with Agent + Human Dialogue feedback for more transparent and controllable audit processes
• Custom Audit Standards: Support custom audit rule configuration via YAML/JSON, provide best practice templates for common frameworks

⭐ If this project helps you, please give us a Star! Your support is our motivation to keep moving forward!

This disclaimer is intended to clarify the responsibilities and risks associated with the use of this open source project and to protect the legitimate rights and interests of project authors, contributors and maintainers. The code, tools and related content provided by this open source project are for reference and learning purposes only.

• ⚠️ Important Notice: This tool analyzes code by calling third-party LLM service provider APIs, which means your code will be sent to the servers of the selected LLM service provider.
• It is strictly prohibited to upload the following types of code:
  • Code containing trade secrets, proprietary algorithms, or core business logic
  • Code involving state secrets, national defense security, or other classified information
  • Code containing sensitive data (such as user data, keys, passwords, tokens, etc.)
  • Code restricted by laws and regulations from being transmitted externally
  • Proprietary code of clients or third parties (without authorization)
• Users must independently assess the sensitivity of their code and bear full responsibility for uploading code and any resulting information disclosure.
• Recommendation: For sensitive code, please wait for future local model deployment support in this project, or use privately deployed LLM services.
• Project authors, contributors, and maintainers assume no responsibility for any information disclosure, intellectual property infringement, legal disputes, or other losses resulting from users uploading sensitive code.

• The code analysis results and suggestions provided by this tool are for reference only and do not constitute professional security audits, code reviews, or legal advice.
• Users must combine manual reviews, professional tools, and other reliable resources to thoroughly validate critical code (especially in high-risk areas such as security, finance, or healthcare).

• This project is provided "as is" without any express or implied warranties, including but not limited to merchantability, fitness for a particular purpose, and non-infringement.
• Authors, contributors, and maintainers shall not be liable for any direct, indirect, incidental, special, punitive, or consequential damages, including but not limited to data loss, system failures, security breaches, or business losses, even if advised of the possibility.

• This tool relies on AI models such as Google Gemini, and results may contain errors, omissions, or inaccuracies, with no guarantee of completeness or reliability.
• AI outputs cannot replace human expert judgment; users are solely responsible for the final code quality and any outcomes.

• This project integrates multiple third-party LLM services including Google Gemini, OpenAI, Claude, Qwen, DeepSeek, as well as Supabase, GitHub, and other services. Usage is subject to their respective terms of service and privacy policies.
• Code Transmission Notice: User-submitted code will be sent via API to the selected LLM service provider for analysis. The transmission process and data processing follow each service provider's privacy policy.
• Users must obtain and manage API keys independently; this project does not store, transmit, or process user API keys and sensitive information.
• Availability, accuracy, privacy protection, data retention policies, or disruptions of third-party services are the responsibility of the providers; project authors assume no joint liability.
• Data Retention Warning: Different LLM service providers have varying policies on API request data retention and usage. Users should carefully read the privacy policy and terms of use of their chosen service provider before use.

• Users must ensure their code does not infringe third-party intellectual property rights, does not contain confidential information, and complies with open-source licenses and applicable laws.
• Users bear full responsibility for the content, nature, and compliance of uploaded code, including but not limited to:
  • Ensuring code does not contain sensitive information or trade secrets
  • Ensuring they have the right to use and analyze the code
  • Complying with data protection and privacy laws in their country/region
  • Adhering to confidentiality agreements and security policies of their company or organization
• This tool must not be used for illegal, malicious, or rights-infringing purposes; users bear full legal and financial responsibility for all consequences. Authors, contributors, and maintainers shall bear no responsibility for such activities or their consequences and reserve the right to pursue abusers.

• Code, content, or suggestions from contributors do not represent the project's official stance; contributors are responsible for their accuracy, security, and compliance.
• Maintainers reserve the right to review, modify, reject, or remove any contributions.

For questions, please contact maintainers via GitHub Issues. This disclaimer is governed by the laws of the project's jurisdiction.