Xingsandesu/CarrotAI

AI Agent with Multi-Server Streaming & Multi-Language Support
Flutter Frontend + FastAPI Backend
🚀 Experience online now | SaaS Client download
🇨🇳 阅读中文文档
## 🥕 Introduction
CarrotAI is a cutting-edge AI agent application that delivers real-time streaming chat via Server-Sent Events (SSE) and streamable HTTP with built-in Model Control Protocol (MCP) integration. It supports concurrent connections to multiple SSE MCP servers and provides user interfaces in English, Chinese, and Japanese.
## 🚀 Features
AI Agent: Real-time chat powered by SSE and MCP adapters for a seamless conversational experience.
Multi-Server Support: Connect to and call multiple SSE MCP servers simultaneously to aggregate intelligent responses.
Multi-Language: Full localization in English, 中文 (Chinese), and 日本語 (Japanese).
Deep Thinking Mode: Advanced analysis for complex or multi-step queries.
Authentication: Secure login/register flow using JWT tokens.
Responsive UI: Adaptive design for mobile, desktop, and web platforms.
Theme Customization: Light/dark mode, custom seed colors, and dynamic Material 3 theming via dynamic_color.
File Upload: Attach and parse files within conversations for richer context.
## 🤖 Supported Model APIs
DeepSeek: Advanced language model with strong reasoning capabilities
## 🛠️ Tech Stack
### Frontend
Framework: Flutter
State Management: Provider
UI: Material Design 3
Localization: flutter gen-l10n
Theming: dynamic_color
### Backend
Framework: FastAPI
Streaming: Server-Sent Events (SSE)
AI Integration: DeepSeek LLM, MCP (Model Control Protocol)
Database: PostgreSQL + SQLAlchemy
Authentication: JSON Web Tokens
Migrations: Alembic
Deployment: Uvicorn & Gunicorn
## 📋 Prerequisites
Flutter SDK ^3.7.2
Python >=3.12
PostgreSQL
## ⚡ Quick Start
> Please make sure that it has been installed. uv
bash
# Clone repository
git clone https://github.com/Xingsandesu/CarrotAI.git && cd CarrotAI
# Deal with environment variables
mv backend/.env.example backend/.env && mv .env.example .env
# Edit environment variables
vim .env
vim backend/.env
# Temporarily start PostgreSQL
docker-compose -f docker-compose.yml -f docker-compose.override.yml up -d postgres
# Backend setup
uv run backend/scripts/startup.py --user --email --username --password
# Stop PostgreSQL
docker-compose -f docker-compose.yml -f docker-compose.override.yml down
# Deal with Config
vim config/
# Run Backend
docker compose up -d
## 🔧 Installation
### Backend Setup
1. Navigate to the backend directory:
bash
cd backend
2. Create and activate a virtual environment:
bash
uv sync
3. Copy the example environment file:
bash
cp .env.example .env
4. Apply database migrations:
bash
uv run scripts/init_db.py && uv run scripts/init_config.py
6. Run the server:
bash
python main.py # Development mode
python main.py prod # Production mode with Gunicorn
### Frontend Setup
1. Return to the project root:
bash
cd ..
2. Fetch Flutter dependencies:
bash
flutter pub get
3. Generate localization files:
bash
flutter gen-l10n
4. Launch the app:
bash
flutter run
5. Build for web:
bash
flutter build web --wasm
## 🌐 Configuration
Frontend: Edit lib/core/config/app_config.dart for API endpoints and theming defaults.
Backend: Configure .env and backend/app/core/config.py for database, and MCP servers.