Skip to content
forked from sweepai/sweep

Sweep: open-source AI-powered Software Developer for small features and bug fixes.

License

Notifications You must be signed in to change notification settings

sweepai/sweep-hearth

 
 

Repository files navigation

Github Issues ⟶  Pull Requests!

Install Sweep Github App Docker Pulls Docs PyPI version Self Host Sweep Docker Image Python Unit Tests


Sweep is an AI junior developer that turns bugs and feature requests into code changes. Sweep automatically handles devex improvements like adding typehints/improving test coverage. 🤖

Install Sweep and open a Github Issue like: Sweep: Add typehints to src/utils/github_utils.py and Sweep will:

  1. Search through your codebase to find the dependencies of github_utils.py
  2. Modify the code to add typehints
  3. Run and debug your code to write a Pull Request

Features

  • Turns issues directly into pull requests (without an IDE)
  • Addresses developer replies & comments on its PRs
  • Understands your codebase using the dependency graph, text, and vector search.
  • Runs your unit tests and autoformatters to validate generated code.
  • Stack small fixes into your PR by applying Sweep Rules

Sweep Youtube Tutorial

Note

What makes Sweep Different

We've been addressing code modification using LLMs for a while. We found and are fixing a lot of issues.

  • Modifying Code - LLMs like GPT4 don't have a great way to automatically modify code. We heavily experiment on different ways to modify code so you don't have to. We've spent a really long time working on this - check out https://docs.sweep.dev/blogs/gpt-4-modification!
  • Planning Code Changes - Retrieval-Augmented-Generation isn't enough. We wrote a code chunker that's used fairly heavily, and we're constantly improving this: https://docs.sweep.dev/blogs/chunking-improvements
  • Sweep runs your Github Actions, catching bugs and making sure each line of new code has been properly validated!
  • Sweep uses it's sandbox to format your code, and uses Rules to perform other changes like adding typehints, or any other small chores!

Getting Started

GitHub App

Install Sweep by adding the Sweep GitHub App to your desired repositories.

  • For more details, visit our installation page.

  • Note: Sweep only considers issues with the "Sweep:" title on creation and not on update. If you want Sweep to pick up an existing issue, you can add the "Sweep" label to the issue.

  • We focus on Python but support all languages GPT-4 can write. This includes JS/TS, Rust, Go, Java, C# and C++.


Story

We used to work in large, messy repositories, and we noticed how complex the code could get without regular refactors and unit tests. We realized that AI could handle these chores for us, so we built Sweep!

Unlike existing AI solutions, Sweep can solve entire tickets and can be parallelized + asynchronous: developers can spin up 10 tickets and Sweep will address them all at once.

Pricing

Every user receives unlimited GPT-3.5 tickets and 5 GPT-4 tickets per month. For professionals who want to try unlimited GPT-4 tickets and priority support, you can get a one week free trial of Sweep Pro.

For more GPT-4 tickets visit our payment portal!

You can get enterprise support by contacting us.


Warning

Limitations of Sweep

  • Large-scale refactors: > 10 files or > 400 lines of code changes * e.g. Refactor the entire codebase from TensorFlow to PyTorch * If this is a use case you're looking forward to, let us know!
  • Editing images and other non-text assets * e.g. Create favicons for our landing page * We can, however, read images.

Contributing

Contributions are welcome and greatly appreciated! To get set up, see Development. For detailed guidelines on how to contribute, please see the CONTRIBUTING.md file.

Contributors

Thank you for your contribution!

and, of course, Sweep!

About

Sweep: open-source AI-powered Software Developer for small features and bug fixes.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 48.6%
  • Python 44.3%
  • TypeScript 6.2%
  • Shell 0.5%
  • CSS 0.1%
  • JavaScript 0.1%
  • Other 0.2%