gpt-all-star 0.0.4

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.

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.

Table of contents

• 🏛 Concept
• 🐳 Getting Started
  • For User
  • For Developer
• 🕴 Current Situation
• 🔎 Examples
  • ⏱️ Pomodoro Timer

🏛 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.

🐳 Getting Started

For User

1. Installation

$ pip install gpt-all-star

2. Set the GPT ALL STAR environment variables

$ export OPENAI_API_MODEL_NAME=gpt-4-turbo-preview
$ export OPENAI_API_KEY=<your-openai-api-key>

3. 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 [e-mail]:kyaukyuai/gpt-all-star.git

2. Edit the .env file

$ mv .env.sample .env

# OPENAI or AZURE
ENDPOINT=OPENAI

# USE when ENDPOINT=OPENAI
OPENAI_API_MODEL_NAME=gpt-4-1106-preview
OPENAI_API_KEY=<your-openai-api-key>

# USE when ENDPOINT=AZURE
AZURE_OPENAI_API_KEY=<your-azure-opnai-api-key>
AZURE_OPENAI_ENDPOINT=https://<your-azure-openai-endpoint>.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=<your-azure-openai-deployment-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>

3. Run docker compose build and docker compose up

$ make build
$ make up

4. Open the web terminal port 7681

Open: http://localhost:7681

5. Install dependencies

$ poetry install

6. 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|improvement|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.                                 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

7. 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.

🔎 Examples

⏱️ Pomodoro Timer

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