Skip to content

Repository files navigation

BuildMate

An AI agent that generates complete, runnable software projects from natural language prompts. Users describe what they want to build, and the agent returns a fully structured codebase ready to run.

Architecture

  • Planner Agent – Analyzes your request and generates a detailed project plan.
  • Architect Agent – Breaks down the plan into specific engineering tasks with explicit context for each file.
  • Coder Agent – Implements each task, writes directly into files, and uses available tools like a real developer.
Coder Agent Architecture

Getting Started

Prerequisites

  • Make sure you have uv installed, follow the instructions here to install it.
  • Ensure that you have created a groq account and have your API key ready. Create an API key here.

Installation and Startup

  • Create a virtual environment using: uv venv and activate it using source .venv/bin/activate
  • Install the dependencies using: uv pip install -r pyproject.toml
  • Create a .env file and add the variables and their respective values mentioned in the .sample_env file

Now go to the graph.py file located in THE_BOSS_AGENT and write ur prompt in the user prompt at the bottom.

And the we can start the application using the following command:

  cd ./THE_BOSS_AGENT/
  python graph.py

I have used groq here for integrating free models into my project but you can feel free to integrate any model. After adding your API KEY change models as you like to experiment with various results.

MY PERSONAL FAVOURITE: meta-llama/llama-prompt-guard-2-22m

About

An AI agent that generates complete, runnable software projects from natural language prompts. Users describe what they want to build, and the agent returns a fully structured codebase ready to run.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages