WebMaker AI

WebMaker AI is a simple agentic AI application that generates web applications using multiple AI agents.

This project was created for learning purposes to understand how agentic AI workflows can be used to plan, design, and generate application code.

The application mainly includes three agents:

1. Planner Agent

The Planner Agent is responsible for creating the initial plan for the application.

It plans:

• The technology stack
• The main features of the application
• The files that need to be generated

2. Architect Agent

The Architect Agent is responsible for planning the exact implementation steps.

It decides:

• What each file should contain
• How the files should work together
• The structure of the generated application
• The implementation flow for the Coder Agent

3. Coder Agent

The Coder Agent is responsible for generating the actual code.

It uses tools such as:

• Read file
• Write file

Using these tools, the Coder Agent creates and updates the required project files based on the plan created by the Planner Agent and Architect Agent.

Setup Instructions

1. Clone the Repository

git clone https://github.com/lakshanpd/webmaker-ai.git
cd webmaker-ai

2. Install Dependencies

Install the required dependencies using:

pip install -r requirements.txt

3. Create Environment File

Create a .env file in the root directory of the project.

touch .env

Add your Gemini API key inside the .env file:

GEMINI_API_KEY=your_gemini_api_key_here

4. Run the Project

Run the application using:

python -m agent.graph

Credits

Special thanks to the YouTube channel codebasics for the helpful tutorial that helped me build this project.

Tutorial video: Watch on YouTube