Autonomous coding agent with iterative refinement
Planning Agent: Breaks down requirements into concrete tasks
Research Agent: Gathers relevant technical knowledge
Executor Agent: Generates complete, working code files
Critic Agent: Validates output quality and provides feedback
Automatic file extraction from code blocks
Iterative improvement (up to 5 cycles)
ZIP download of generated projects
Use cases: Generate full applications, build React components, create Python scripts, scaffold entire projects
Multi-Agent Pipeline Pattern
User Request
β
[Planner Agent] βββ Task Breakdown
β
[Researcher Agent] βββ Knowledge Gathering
β
[Executor Agent] βββ Output Generation
β
[Critic Agent] βββ Quality Check
β
Pass? ββNoβββ Feedback Loop (back to Planner)
β Yes
Final Output
- Python 3.8+
- OpenAI API key
- Clone the repository
git clone https://github.com/blakebrandon-hub/Multi-Agent-Code-Generator- Install dependencies
pip install -r requirements.txt- Set OpenAI API key
export OPENAI_API_KEY='your-api-key-here'- Run the application
python app.py- Open in browser
http://localhost:5000