🛡️ AI Code Audit Toolkit

A unified, multi-model workflow for automated code auditing, leveraging both local LLMs and cloud-based Web AI services.

The AI Code Audit Toolkit is a comprehensive developer tool designed to streamline code reviews, security checks, and quality assurance. Instead of relying on a single AI model, this toolkit orchestrates a unified workflow across 6 distinct AI endpoints, allowing you to choose the right model for the right job—whether you need offline privacy or cloud-scale reasoning.

---

✨ Key Features

• 🔀 Unified Workflow: A single interface to route code audit tasks to multiple AI backends seamlessly.
• 🏠 Local-First Privacy: Run sensitive code audits entirely offline using local LLMs (Hermes, NIM, MiniMax-M3).
• ☁️ Cloud-Powered Depth: Fallback or escalate complex audits to 5 integrated Web AI services for deeper analysis.
• ⚡ High Performance: Optimized routing to ensure fast feedback loops during CI/CD pipelines or local development.
• 🔌 Extensible Architecture: Easily add new AI endpoints or customize audit prompts.

---

🏗️ Supported AI Endpoints

The toolkit is pre-configured to support a hybrid mix of local and cloud models:

Category	Model / Service	Type	Best Used For
Local	Hermes	LLM	General code review & privacy-focused audits.
Local	NIM	LLM	High-throughput, low-latency local inference.
Local	MiniMax-M3	LLM	Complex logic, architecture reasoning, & deep refactoring.
Web	Web AI Service 1-5	API	Cloud-based deep analysis, multi-file context, & specialized security scanning.

(Note: Web AI service names can be configured in your environment variables).

---

🚀 Getting Started

Prerequisites

• Git
• Python 3.10+ / Node.js 18+ (Adjust based on your project's language)
• Local LLM setup (Ollama / LM Studio) if running local endpoints.
• API Keys for Web AI services.

Installation

1. Clone the repository:

   git clone https://github.com/afuckingco/code-audit-toolkit.git
   cd code-audit-toolkit

2. Install dependencies:

   # Example for Python
   pip install -r requirements.txt
   
   # Or for Node.js
   npm install

3. Configure Environment Variables: Copy the example env file and fill in your API keys and endpoint URLs.

   cp .env.example .env

   Open .env and configure your local ports and Web AI API keys.

---

🛠️ Usage

Run the audit toolkit against your target codebase:

# Example command (adjust to your actual tool command)
python main.py --target ./src --model hermes --audit-type security

Available Commands

• --model: Choose the AI endpoint (hermes, nim, minimax-m3, web-1, etc.)
• --audit-type: Type of audit (security, quality, performance, full)
• --output: Export format (json, markdown, html)

---

🤝 Contributing

We welcome contributions! Whether it's adding a new AI endpoint, fixing a bug, or improving documentation, your help is appreciated.

Please read our Contributing Guidelines to get started.

1. Fork it (git clone https://github.com/afuckingco/code-audit-toolkit.git)
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'feat: add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

---

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

📬 Contact & Support

• Maintainer: @afuckingco
• Issues: Please open a GitHub Issue for bugs or feature requests.

---

Made with ❤️ by afuckingco