https://github.com/dex3r/GPT-Codemaster

Automatic programming by creating Pull Requests from Issues using LLMs
https://github.com/dex3r/GPT-Codemaster

ai automated-programming automated-reasoning automation chatgpt gpt-4 gpt-api llm openai openai-api programming

Last synced: 29 days ago
JSON representation

Automatic programming by creating Pull Requests from Issues using LLMs

• Host: GitHub
• URL: https://github.com/dex3r/GPT-Codemaster
• Owner: dex3r
• License: gpl-3.0
• Created: 2023-03-22T12:31:45.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-03-31T15:19:37.000Z (over 1 year ago)
• Last Synced: 2024-08-03T18:21:36.557Z (4 months ago)
• Topics: ai, automated-programming, automated-reasoning, automation, chatgpt, gpt-4, gpt-api, llm, openai, openai-api, programming
• Language: C#
• Homepage:
• Size: 75.2 KB
• Stars: 55
• Watchers: 3
• Forks: 4
• Open Issues: 6
• Metadata Files:
  • Readme: Readme.md
  • License: LICENSE

Awesome Lists containing this project

• stars - dex3r/GPT-Codemaster - Automatic programming by creating Pull Requests from Issues using LLMs (C# #)

README

        
# GPT-Codemaster

Automatic programming by creating Pull Requests from Issues using LLMs.

An experimental project to automate programming. It uses a task-based approach to move a software project development forward by reading task descriptions from Github Issues and implementing them in a Pull Request.

Example Pull Requests created with this tool are available [here](https://github.com/dex3r/GPT-Codemaster/pulls?q=is%3Apr+label%3A%22GPT-Codemaster+example%22+)

## Features

 - [x] Modifying files 

 - [x] Creating new files

 - [x] Automatic reacting to Issues with the specified label

 - [x] Creating Pull Requests

 - [ ] Released as Github Action in the marketplace

 - [ ] Automatic creation of tests for it's implementation

 - [ ] Reacting to Pull Requests checks

 - [ ] Back-and-forth conversation and reacting to human feedback in a Pull Request

 - [ ] Implement Reflection (https://arxiv.org/pdf/2303.11366.pdf and https://nanothoughts.substack.com/p/reflecting-on-reflexion)

 - [ ] Being able to go though massive projects

 - [ ] Read .ai/project_description_short.json of every project and include it in the prompt

 - [ ] Easy attachment of different LLMs, inlucing locally hosted

## Tests

 - [x] Comlpete a simple Issue, [example](https://github.com/dex3r/GPT-Codemaster/pull/2)

 - [ ] Complete a more complex issue

## FAQ 

### Does it work?

Sometimes, and only for small projects with small files, like this one. The biggest limitation right now is the tokens length for LLMs.

### Does it _really_ work?

It's an experiment, not an actual product.

### What do I need to use it?

1. GPT-4 API access and token

1. Github repository

1. This project as a GitHub Action

1. Enable "Allow Github Actions to create pull requests" in settings