AI-Powered library that generates your complete Code Base!

How to build an entire project using AI in minutes? Use this open-source library named gpt-engineer.

How does GPT engineer work?

gpt-engineer is very easy to use. You give instructions on what you want to build. AI analyzes it, asks you for a few more questions for clarification, and then generates a codebase. You can also incrementally build it and improve it by giving more prompts.

Core features

• One prompt generates a codebase
• Asks clarifying questions
• Generates technical spec
• Writes all necessary code
• Easy to add your own reasoning steps, modify, and experiment
• Open source
• Lets you finish a coding project in minutes.

Project philosophy

• Simple to get value
• Flexible and easy to add new own “AI steps”.
• Incrementally build towards a user experience of:
  1. high-level prompting
  2. giving feedback to the AI that it will remember over time
• Fast handovers back and forth between AI and human
• Simplicity, all computation is “resumable” and persisted to the filesystem

Usage

Choose either stable or development.

For stable release:

• pip install gpt-engineer

For development:

• cd gpt-engineer
• make install
• source venv/bin/activate

Setup

With an api key that has GPT4 access run:

• export OPENAI_API_KEY=[your api key]

Run:

• Create an empty folder. If inside the repo, you can run:
  • cp -r projects/example/ projects/my-new-project
• Fill in the main_prompt file in your new folder
• Run: gpt-engineer projects/my-new-project

Results

• Check the generated files in projects/my-new-project/workspace

Implementing additional chain of thought prompting, e.g. Reflexion, should be able to make it more reliable and not miss requested functionality in the main prompt.

Sharing prompts across the projects

You can specify the “identity” of the AI agent by editing the files in the identity folder.

Editing the identity, and evolving the main_prompt, is currently how you make the agent remember things between projects.

Each step in steps.py will have its communication history with GPT4 stored in the logs folder, and can be rerun with scripts/rerun_edited_message_logs.py.