gpt-engineer icon indicating copy to clipboard operation
gpt-engineer copied to clipboard

Specify what you want it to build, the AI asks for clarification, and then builds it.

GPT Engineer

Discord Follow GitHub Repo stars Twitter Follow

Specify what you want it to build, the AI asks for clarification, and then builds it.

GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.


Project philosophy

  • Simple to get value
  • Flexible and easy to add new own "AI steps". See
  • 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


Choose either stable or development.

For stable release:

  • pip install gpt-engineer

For development:

  • git clone
  • cd gpt-engineer
  • pip install -e .
    • (or: make install && source venv/bin/activate for a venv)


With an OpenAI API key (preferably with GPT-4 access) run:

  • export OPENAI_API_KEY=[your api key]

Alternative for Windows

  • set OPENAI_API_KEY=[your api key] on cmd
  • $env:OPENAI_API_KEY="[your api key]" on powershell


  • Create an empty folder. If inside the repo, you can run:
    • cp -r projects/example/ projects/my-new-project
  • Fill in the prompt file in your new folder
  • gpt-engineer projects/my-new-project
    • (Note, gpt-engineer --help lets you see all available options. For example --steps use_feedback lets you improve/fix code in a project)

By running gpt-engineer you agree to our terms.


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

Getting Started with GitHub Codespaces

To get started, create a codespace for this repository by clicking this 👇

Open in GitHub Codespaces


You can specify the "identity" of the AI agent by editing the files in the preprompts folder.

Editing the preprompts, and evolving how you write the project prompt, is currently how you make the agent remember things between projects.

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


The gpt-engineer community is building the open platform for devs to tinker with and build their personal code-generation toolbox.

If you are interested in contributing to this, we would be interested in having you!

You can check for good first issues here. Contributing document here.

We are currently looking for more maintainers and community organisers. Email [email protected] if you are interested in an official role.

If you want to see our broader ambitions, check out the roadmap, and join discord to get input on how you can contribute to it.