Setup Guide

Setup Guide

This guide is self-contained. Every step is copy-pasteable. No external references required.

Prerequisites

• Python 3.10 or later (python.org)
• pip (included with Python 3.10+)
• Git
• A Gemini API key (aistudio.google.com)

Installation

Clone the repository and create a virtual environment:

git clone https://github.com/Coding-Autopilot-System/autogen.git
cd autogen
python -m venv .venv

Activate the virtual environment:

# Windows PowerShell:
.\.venv\Scripts\Activate.ps1
# macOS / Linux:
source .venv/bin/activate

Install the required packages (no requirements.txt — install directly):

pip install agent-framework python-dotenv fastapi uvicorn

Configuration

Copy the example environment file and set your API key:

cp .env.example .env

Open .env and set at minimum:

GEMINI_API_KEY=your_gemini_api_key_here

See the Configuration Reference for all available variables.

Running the Agent

Verify your setup with the doctor command:

python main.py doctor

Run a smoke test with a sample prompt:

python main.py smoke --message "List the files in this repo"

What a Successful Setup Looks Like

After running python main.py doctor, a successful setup produces these observable results:

1. Config printed without error — the doctor command prints your configuration values (MAF_MODEL, MAF_REPO_ROOT, etc.) without raising an exception. The API key value is not printed in full — only its presence is confirmed.
2. No ModuleNotFoundError — all required packages (agent-framework, python-dotenv) are importable without errors.
3. Smoke test returns an agent response — python main.py smoke sends a prompt through the full MAF routing pipeline and returns a text response from the configured model.

If python main.py doctor fails with "command not found", ensure your virtual environment is activated and python main.py is run from the repo root.