sweep: A Python repository from AhalimZaki

Bug Reports & Feature Requests ⟶ Code Changes

Sweep is an AI junior developer that transforms bug reports & feature requests into code changes.

Describe bugs, small features, and refactors like you would to a junior developer, and Sweep:

🔍 reads your codebase
📝 plans the changes
⚡writes a pull request with code⚡

Features 🌠

🌠 Turns issues directly into pull requests (without an IDE)
👀 Addresses developer replies & comments on its PRs
🔎 Uses embedding-based code search

Why Sweep is Unique 🦄

Unlike Copilot, which only provides IDE based autocompletion, Sweep handles the entire flow end-to-end. Unlike ChatGPT, Sweep does not require pasting files.

sweep.mp4

Getting Started 🚀

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 issue after it has been created, you can add the "Sweep" label to the issue.
We support all languages GPT-4 supports, including Python, JS/TS, Rust, Go, Java, C# and C++.

Limitations of Sweep ⚠️

🏗️ Large-scale refactors: >3 files or >150 lines of code changes (we're working on this!)
- e.g. Refactor entire codebase from Tensorflow to PyTorch
⏲️ Using the latest APIs that have changed past 2022
- e.g. Set up a vector store using LlamaIndex Typescript
- 🎩 If you provide the relevant docs however, then Sweep can do this
🖼️ Editing images and other non-text assets
- e.g. Use the logo to create favicons for our landing page
⤵️ Accessing external APIs, including fetching API tokens
- e.g. Set up sign-in using Ethereum

Story 📘

We were frustrated by small tickets, like simple bug fixes, annoying refactors, and small features. Each task required us to open our IDE to fix simple bugs. So we decided to leverage the capabilities of ChatGPT to address this directly in GitHub.

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

The Stack 📚

GPT-4 32k 0613
ActiveLoop DeepLake for Vector DB with MiniLM L12 as our embeddings model
Modal Labs for infra + deployment

Highlights 🌟

Examine pull requests created by Sweep here.

Pricing

We offer unlimited GPT3.5 tickets to every user. You also start with 5 GPT4 credits which are used when a PR is created.

For professionals who want more tickets and priority support/feature requests, check out Sweep Pro now at $480/month. In addition, we're also offering 15 PRs for $60 as a one-time purchase for anyone interested in eventually purchasing Sweep Pro. You can purchase this here.