Sweep Blog

I think they're getting there but missing big features like a high quality "Apply" workflow and next-edit predictions. I'm working with two of my friends to fill the missing pieces as a JetBrains plugin: https://docs.sweep.dev/

I know of Sweep <https://docs.sweep.dev>, but honestly the SOTA on SWE-bench, which is basically exactly what you're asking for, is only about a 25% success rate, so expect very mediocre results.

Thanks for the suggestion! CLI tools can be simple to deploy and setup but are limited in the long run. Running the logic server side allows us to perform way more validation, such as GitHub Actions, linting, and pre-commit hooks. You can do this in your terminal, but it's not as easily parallelized and the process is not as easily persisted. There are definitely some tradeoffs to be made. Also, the onboarding flow for GitHub Apps is significantly smoother and is a familiar interface for many people. We built a CLI-installed tool previously and there were a ton of versioning and environment-related problems etc, with 3 OS's to support. Unfortunately, it becomes harder to focus on building the best tool for our users if our focus is too broad. To your last point, you can pry into our codebase and our blogs to see what we do under the hood; "Watch the magic happen" is just referring to the simplicity of our installation process. Also, we only store the logs for debugging and they only get persisted 30 days (which is also how long OpenAI stores them for). We gave a lot of thought to designing our search engine that doesn't store any code in plaintext. Check it out here: https://docs.sweep.dev/blogs/search-infra

You can use the AST to chunk the code: https://docs.sweep.dev/blogs/chunking-2m-files

Very interesting and honest description of the difficulties and solutions sweep.dev encountered: https://docs.sweep.dev/blogs/gpt-4-modification

Sweep is mentioned as attribution in multiple places a) https://github.com/definitive-io/code-indexer-loop#attribution b) https://github.com/definitive-io/code-indexer-loop/blob/fd9d4a65e475e9… The difference is packaging it as a consumable PyPI package that can easily be used in a project (they even call out for separating this out into a stand alone project but that they lack the time to do so: https://docs.sweep.dev/blogs/chunking-2m-files#future- ) In addition, we expand and fix the implementation, for example it now supports limiting on token count instead of character count, and we fix some white space inconsistencies in parsing/chunk reconstruction.

From the initial look, it looks like you're taking the work of SweepAI, a source-available repo, which gave(?) it to LlamaIndex(1) and then you're just providing a wrapper around the LlamaIndex that provides a way to do an Update statement. 1) https://docs.sweep.dev/blogs/chunking-improvements

Meta-issue: the purple on black text in the examples page is hard to read. https://docs.sweep.dev/examples