Skip to main content
gpt-all-star

PyPI License: MIT

AI-powered code generation tool for scratch development of web applications with a team collaboration of autonomous AI agents. This is a research-project, and its primary value is to explore the possibility of autonomous AI agents.

gpt-all-star-demo

Table of contents

🏛 Concept

  • Build Team, Build App: Simply organize your team and decide on what to build.
  • AI Agent Collaboration: Assemble a group of AI agents and work together to carry out the steps.
    1. Choose the right leader for each step.
    2. Leaders create a plan of action for each step.
    3. Work with team members to complete every task in the action plan.

gpt-all-star-concept

🐳 Getting Started

For User

  1. Installation
$ pip install gpt-all-star
  1. Set the GPT ALL STAR environment variables
$ export OPENAI_API_MODEL=gpt-4o
$ export OPENAI_API_KEY=<your-openai-api-key>
  1. Fun GPT ALL STAR
$ gpt-all-star

For Developer

:bulb: While it's entirely feasible to launch the application on your local machine directly, we strongly recommend using Docker for starting up the application.

  1. Clone the repository
$ git clone git@github.com:kyaukyuai/gpt-all-star.git
  1. Edit the .env file
$ mv .env.sample .env
# OPENAI or AZURE or ANTHROPIC
ENDPOINT=OPENAI

# USE when ENDPOINT=OPENAI
OPENAI_API_MODEL=gpt-4o
OPENAI_API_KEY=<your-openai-api-key>

# USE when ENDPOINT=AZURE
AZURE_OPENAI_API_KEY=<your-azure-openai-api-key>
AZURE_OPENAI_API_VERSION=2024-05-01-preview
AZURE_OPENAI_API_MODEL=<your-azure-openai-api-model>
AZURE_OPENAI_DEPLOYMENT_NAME=<your-azure-openai-deployment-name>
AZURE_OPENAI_ENDPOINT=https://<your-azure-openai-endpoint>.openai.azure.com/

# USE when ENDPOINT=ANTHROPIC
ANTHROPIC_API_KEY=<your-anthropic-api-key>
ANTHROPIC_MODEL=<your-anthropic-model-name>

# LangSmith
LANGCHAIN_TRACING_V2=true
LANGCHAIN_ENDPOINT=https://api.smith.langchain.com
LANGCHAIN_API_KEY=<your-langchain-api-key>
LANGCHAIN_PROJECT=<your-langchain-project>

# This is an environment variable to use if you want to manage the code you want to generate with gpt-all-star on GitHub.
GITHUB_ORG=<your-github-org>
GITHUB_TOKEN=<your-github-token>
  1. Run docker compose build and docker compose up
$ make build
$ make up
  1. Open the web terminal port 7681

Open: http://localhost:7681

  1. Install dependencies
$ poetry install
  1. Start GPT ALL STAR
$ poetry run gpt-all-star
$ poetry run gpt-all-star --help

Usage: gpt-all-star [OPTIONS]

╭─ Options ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ --step                -s      [none|default|build|specification|system_design|development  Step to be performed [default: StepType.DEFAULT]            │
│                               |entrypoint|ui_design|healing]                                                                               │
│ --project_name        -p      TEXT                                                         Project name [default: None]                                │
│ --japanese_mode       -j                                                                   Japanese mode                                               │
│ --review_mode         -r                                                                   Review mode                                                 │
│ --debug_mode          -d                                                                   Debug mode                                                  │
│ --plan_and_solve                                                                           Plan-and-Solve Prompting                                    │
│ --install-completion          [bash|zsh|fish|powershell|pwsh]                              Install completion for the specified shell. [default: None] │
│ --show-completion             [bash|zsh|fish|powershell|pwsh]                              Show completion for the specified shell, to copy it or      │
│                                                                                            customize the installation.                                 │
│                                                                                            [default: None]                                             │
│ --help                                                                                     Show this message and exit.                                 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
  1. Edit the team members

If you want to change the team members, edit the gpt_all_star/agents.yml file.

🕴 Current Situation

This is a research project and the main focus is currently on validating Client Web Applications in React and ChakraUI using JavaScript. We would like to test other languages and libraries as well and welcome contributions.

🧑‍💻️ UI Project

gpt-all-star-ui is a web application that uses gpt-all-star as a backend. It's a simple web application that allows you to use gpt-all-star as a service.

Streamlit App

🔎 Examples

⏱️ Pomodoro Timer

  • 💬 Instruction: Pomodoro Timer fully designed by human interface guideline
  • 💻️ GitHub

Export-1707059574807

🍻 Contribution

GPT ALL STAR is open-source and we welcome contributions. If you're looking to contribute, please:

  • Fork the repository.
  • Create a new branch for your feature.
  • Add your feature or improvement.
  • Send a pull request.
  • We appreciate your input!

Installing Dependencies

poetry lock
poetry install

Virtual Env

poetry shell

Pre-commit hooks

pre-commit install

Packaging

poetry build

Installing Locally

pip install dist/*.tar.gz

Metadata

Release files for gpt-all-star 0.0.64

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gpt-all-star 0.0.64
File Size Uploaded Provenance
gpt_all_star-0.0.64.tar.gz 42.6 kB Without provenance Details

Release files / gpt_all_star-0.0.64.tar.gz

Download URL gpt_all_star-0.0.64.tar.gz
Size 42.6 kB
Tags Source
SHA-256 checksum
How to use checksums
cf76b1d6c7fb6a26ea6a89acde332e4749400c85586ebbdd3971c60acc4a2366
BLAKE2b-256 checksum
How to use checksums
7ea1789f2166f3d9c4b7a1fe792490e08cf2d335fd52017f9feb0da167fe06d1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.0.1 CPython/3.12.8

Security for gpt-all-star 0.0.64

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Release history Release notifications | RSS feed

This release

0.0.64 This release

1 release file No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page