🚀 Software Team - Multi-Agent Development Crew

Welcome to the Software Team project, powered by CrewAI. This is an autonomous multi-agent AI system that simulates a complete software development team, capable of taking high-level requirements and producing fully functional Python applications with backend logic, frontend interfaces, and comprehensive tests.

🤖 What is CrewAI?

CrewAI is a cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks through a multi-agent approach.

💡 Key Concepts

🔗 Multi-Agent Systems Unlike single-agent approaches, multi-agent systems distribute tasks among specialized agents, each with distinct roles, goals, and expertise. This enables:

• ⚡ Specialization: Each agent focuses on what it does best
• 🤝 Collaboration: Agents share context and build upon each other's work
• 📈 Scalability: Complex problems are broken down into manageable subtasks
• 🛡️ Resilience: Multiple agents can validate and improve outcomes

⚙️ How CrewAI Works

1. 🧠 Agents: Autonomous units with specific roles, goals, and backstories that guide their behavior
2. 📋 Tasks: Discrete assignments with clear descriptions, expected outputs, and dependencies
3. 🔄 Process: Orchestration strategy (sequential, hierarchical, or parallel) that determines workflow
4. 🔧 Tools: External capabilities agents can leverage to perform actions
5. 💾 Memory: Shared context that enables agents to learn from previous interactions

👥 This Project: A Software Development Team

This crew simulates a real software development team with four specialized agents:

1. Engineering Lead 👔

   • Reviews requirements and creates detailed technical designs
   • Defines module structure, classes, and method signatures
   • Outputs architecture documentation

2. Backend Engineer 💻

   • Implements the design in clean, efficient Python code
   • Creates self-contained, production-ready modules
   • Follows software engineering best practices

3. Frontend Engineer 🎨

   • Builds Gradio-based user interfaces
   • Creates interactive demos of backend functionality
   • Ensures simple, user-friendly experiences

4. Test Engineer 🧪

   • Writes comprehensive unit tests
   • Validates backend implementation
   • Ensures code quality and reliability

Workflow: The crew operates in a sequential process, where each agent builds upon the previous agent's output, creating a natural software development pipeline: Design → Implementation → UI → Testing.

📦 Installation

Ensure you have Python >=3.10 <3.14 installed on your system. This project uses UV for dependency management and package handling, offering a seamless setup and execution experience.

📥 Step 1: Install UV

If you haven't already, install UV:

pip install uv

🔗 Step 2: Install Dependencies

Navigate to your project directory and install the dependencies:

crewai install

This will lock and install all required dependencies including:

• CrewAI 1.9.0 with Google Gemini integration
• Gemini 2.0 Flash model support
• Gradio for UI development
• All necessary tools and utilities

🔑 Step 3: Configure API Keys

Create a .env file in the root directory with your API credentials:

# Google Gemini API Key (required)
GEMINI_API_KEY=your_gemini_api_key_here

# Optional: SerperDev API Key for web search capabilities
SERPER_API_KEY=your_serper_api_key_here

Note: This project uses Google's Gemini 2.0 Flash model (gemini-2.0-flash-001) for all agents. Get your API key from Google AI Studio.

🎨 Customization

The crew can be fully customized to match your specific needs:

🤖 Agent Configuration

Edit src/src/config/agents.yaml to:

• Modify agent roles, goals, and backstories
• Change the LLM model for each agent
• Add or remove agents from the team
• Configure agent-specific parameters (code execution, retry limits, etc.)

📋 Task Configuration

Edit src/src/config/tasks.yaml to:

• Define new tasks or modify existing ones
• Set task dependencies and context
• Customize expected outputs and file locations
• Adjust task descriptions and requirements

⚙️ Crew Logic

Edit src/src/crew.py to:

• Add custom tools for your agents
• Modify the process type (sequential, hierarchical, parallel)
• Configure agent-specific settings (verbosity, execution modes, timeouts)
• Implement custom crew behaviors

🔧 Input Configuration

Edit src/src/main.py to:

• Customize the input parameters for your crew
• Add validation logic
• Define custom execution triggers
• Implement training and testing workflows

▶️ Running the Project

To kickstart your crew of AI agents and begin task execution, run this from the root folder of your project:

$ crewai run

This command initializes the src Crew, assembling the agents and assigning them tasks as defined in your configuration.

This example, unmodified, will run the create a report.md file with the output of a research on LLMs in the root folder.

📚 Understanding Your Crew

The src Crew is composed of multiple AI agents, each with unique roles, goals, and tools. These agents collaborate on a series of tasks, defined in config/tasks.yaml, leveraging their collective skills to achieve complex objectives. The config/agents.yaml file outlines the capabilities and configurations of each agent in your crew.

💬 Support

For support, questions, or feedback regarding the Software Team or CrewAI:

• 📖 Visit our documentation
• 🐙 Reach out to us through our GitHub repository
• 💬 Join our Discord
• 🤖 Chat with our docs

✨ Let's create wonders together with the power and simplicity of CrewAI!