raaj2493/TrustGuard
TrustGuard は 🤖 AI ベースのバックエンド API で、⚡ Go で構築されており、リアルタイムでユーザー生成テキストの 🚫 攻撃性、 📩 スパム、および 🔍 信頼性を分析・分類します。開発者が 🔐 より安全で、よりスマートかつ信頼性の高いアプリケーションを簡単に構築できるように支援します。
- Stars
- 1
- Forks
- 1
- 最終プッシュ（UTC）
- 2026/04/09
- プロジェクト状態
- 公開中
Raaj Giri ↗
技術トピック
元の README
以下は英語原文のスナップショットです。最新版は GitHub をご覧ください。
README を開く / 閉じる
🛡️ TrustGuard --- AI-Powered Content Safety & Trust Analysis API
🤖 Analyze user-generated content in real-time for toxicity, spam, and trustworthiness using AI.
🚀 Overview
TrustGuard is a high-performance backend API built with ⚡ Go (Golang) that leverages AI to evaluate the safety and reliability of text.
It helps developers build 🔐 secure and trustworthy platforms by detecting:
- 🚫 Toxic content\
- 📩 Spam messages\
- ⚠️ Harmful or suspicious text\
- 🔍 Trustworthiness score
Perfect for 💬 chat apps, 🌐 social media platforms, 📝 review systems, and more.
✨ Features
- ⚡ Fast and lightweight REST API (Go + Gin)
- 🧠 AI-powered text analysis
- 🚫 Toxicity detection
- 📩 Spam classification
- 🔍 Trust scoring system
- 📊 Clean JSON responses
- 🔐 Secure
.envconfiguration - 🧩 Scalable project architecture
- 🔄 Easy frontend integration
🏗️ Tech Stack
Layer Technology
Backend Go (Golang) Framework Gin AI Service Google Gemini API Config godotenv (.env) Testing Thunder Client/Postman
📁 Project Structure
TrustGuard/ ├── backend/ │ ├── controllers/ │ ├── routes/ │ ├── services/ │ ├── config/ │ ├── models/ │ ├── utils/ │ ├── main.go │ └── go.mod ├── frontend/ ├── .env └── README.md
⚙️ Prerequisites
- 🐹 Go (v1.20+)
- 🔑 Gemini API Key
- 📦 Git
🔑 Environment Setup
Create a .env file:
GEMINI_API_KEY=your_api_key_here
PORT=8080
🚀 Installation
git clone https://github.com/raajgiri/TrustGuard.git
cd trustguard/backend
go mod tidy
go run main.go
📡 API
POST /analyze
Request: { "text": "Hello world" }
Response: { "status": "success", "analysis": { "toxicity": "low", "spam": false, "trust_score": 0.87 } }
⭐ Support
Give a ⭐ if you like the project!
📜 License
MIT License