# codegenx

**Repository Path**: mirrors/codegenx

## Basic Information

- **Project Name**: codegenx
- **Description**: CodeGenX 是一个由人工智能驱动的代码生成系统，它以 Visual Studio 代码扩展的形式提供给你，并且是免费的和开源的
- **Primary Language**: JavaScript
- **License**: MPL-2.0
- **Default Branch**: master
- **Homepage**: https://www.oschina.net/p/codegenx
- **GVP Project**: No

## Statistics

- **Stars**: 3
- **Forks**: 0
- **Created**: 2021-11-24
- **Last Updated**: 2025-12-13

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# CodeGenX

**CodeGenX is back online! 🎉**
_We are sorry for the long wait_

Existing users will need to update the extension in VsCode and New users can sign up on our [website](https://deepgenx.com)

<br/>

<!-- <img src="assets/hero-image.png" alt="CodeGenX Logo"> -->

<p align="center">
<img src="CodeGenX_demo.gif" width="800"/>
</p>

CodeGenX is a Code Generation system powered by Artificial Intelligence! It is delivered to you in the form of a Visual Studio Code Extension and is **Free and Open-source**! 

<br/>

## Installation

You can find installation instructions and additional information about CodeGenX in the documentation [here](https://docs.deepgenx.com).

<br/>

## About CodeGenX

### 1. Languages Supported

CodeGenX currently only supports Python. We are planning to add additional languages in future releases.

### 2. Modules Trained On

CodeGenX was trained on Python code which covers many of its common uses. Some libraries which CodeGenX is specifically trained on are:

1. Tensorflow
2. Pytorch
3. Scikit-Learn
4. Pandas
5. NumPy
6. OpenCV
7. Django
8. Flask
9. PyGame

### 3. How CodeGenX Works

At the core of CodeGenX lies a large neural network called [GPT-J](https://github.com/kingoflolz/mesh-transformer-jax). GPT-J is a 6 billion parameter transformer model which was trained on hundreds of gigabytes of text from the internet. We fine-tuned this model on a dataset of open-source python code. This fine-tuned model can now be used to generate code when given an input with the right instructions.

<br/>

## Contributors ✨

This project would not have been possible without the help of these wonderful people:

<br/>

<table>
  <tr>
    <td align="center"><a href="https://github.com/Aryagm"><img src="https://avatars.githubusercontent.com/u/80019072?v=4" width="100px;" alt=""/><br /><sub><b>Arya Manjaramkar</b></sub></a></td>
    <td align="center"><a href="https://github.com/Matthias1590"><img src="https://avatars.githubusercontent.com/u/48327140?v=4" width="100px;" alt=""/><br /><sub><b>Matthias Wijnsma</b></sub></a><br /></td>
    <td align="center"><a href="https://github.com/ThomasHoutrique"><img src="https://avatars.githubusercontent.com/u/30757539?v=4" width="100px;" alt=""/><br /><sub><b>Thomas Houtrique</b></sub></a><br /></td>
    <td align="center"><a href="https://github.com/dome272"><img src="https://avatars.githubusercontent.com/u/61938694?v=4" width="100px;" alt=""/><br /><sub><b>Dominic Rampas</b></sub></td>
    <td align="center"><a href="https://github.com/LelouBil"><img src="https://avatars.githubusercontent.com/u/13931833?v=4" width="100px;" alt=""/><br /><sub><b>Bilel Medimegh</b></sub></td>
    <td align="center"><a href="https://github.com/orgs/DeepGenX/people/josh-hills"><img src="https://avatars.githubusercontent.com/u/57681652?v=4" width="100px;" alt=""/><br /><sub><b>Josh Hills</b></sub></td>
    <td align="center"><a href="https://github.com/Simplyalex99"><img src="https://avatars.githubusercontent.com/u/42325851?v=4" width="100px;" alt=""/><br /><sub><b>Alex</b></sub></td>
  </tr>
  <tr>
    <td align="center"><a href="https://github.com/timothebot"><img src="https://avatars.githubusercontent.com/u/65387160?v=4" width="100px;" alt=""/><br /><sub><b>Tiimo</b></sub></td>
  </tr>
</table>

## Acknowledgements

Many thanks to the support of the Google TPU Research Cloud for providing the precious compute needed for this project.