yek

I made yek for myself because I realized unless I give models the entire relevant code I wasn't getting good results https://github.com/mohsen1/yek

I am planning to add similar concepts to Yek. Either tree-sitter or ast-grep. Your work here and Aider's work would be my guiding prior art. Thank you for sharing! https://github.com/mohsen1/yek

https://github.com/bodo-run/yek/pull/213 here is an example of mostly automated work. It's a small feature but it was done perfectly

A repository serializer is a tool that takes your repository and serializes it into an LLM ingestable format. I used to be a heavy user of yek[0] until recently, because my workflow is basically copy and pasting back and forth to and from Google Gemini. [0]: https://github.com/bodo-run/yek However, as I incorporated a practice of maintaining an llms/ directory in my project (where I put various docs, e.g. .md files from llms.txt), I found that the format yek used (basically ">>>> {file name}\n{file content}") was confusing the LLM; it didn't know which files were part of your project and which files were just docs (it was editing code examples). So I wrote my own thing which categories your files into source code files, documentation files, and other files. Each category is labelled appropriately and the LLM is able to understand what it

yek makes it a bit quicker and you can do all your piping with it: https://github.com/bodo-run/yek

or https://github.com/bodo-run/yek

https://github.com/bodo-run/yek This is more sophisticated for serializing your repo. Please check it out and let me know what do you think?

It seems that most solutions focus on providing an LLM with the code (and sometimes the test failures) and then asking it to produce a new version that might work. I’ve had great success with this method already and even built a serialization CLI tool [1]. However, with O3-Mini, I’ve noticed something new. O1-Mini is both capable and fast. My previous workflow involved waiting quite a bit for the LLM to respond, so I didn’t mind spending time on: 1. Collecting the relevant code 2. Fixing minor issues in the generated code But now, most of my time is spent making small fixes to the AI-generated code. Many of these “bad responses from the AI” could be avoided if the AI had insight into the runtime values of the variables in the code. I believe it would be very beneficial to have IDE-like, debugger-mode interactions with the LLM. Imagine s

Yes! I've done something like this here in my repo. This was nice while lasted (Deepseek is practically useless through the API since yesterday) https://github.com/bodo-run/yek/blob/main/.github/workflows/... https://github.com/bodo-run/yek/blob/main/scripts/ai-loop.sh Using askds https://github.com/bodo-run/askds

I am subscribed to o1 Pro and am working on a little Rust crate. I asked both o1 Pro and Deepseek R1 to write e2e tests given all of the code in the repo (using yek[1]). o1 Pro code: https://github.com/bodo-run/clap-config-file/pull/3 Deepseek R1: https://github.com/bodo-run/clap-config-file/pull/4 My judgement is that Deepseek wrote better tests. This repo is small enough for making a judgement by reviewing the code. Neither pass tests. [1] https://github.com/bodo-run/yek

I use yek https://github.com/bodo-run/yek

Hi HN, Following the release of yek[1] I am releasing this tool which is an evolution of my script that I was using to debug tests with R1 without doing too much copy-pasting. You can update the prompt to explicitly return a diff and automate applying the suggestion and trying again too if you trust AI that much! Please let me know what do you think! [1] https://github.com/bodo-run/yek

I use Cursor Editor and the Claude edit mode is extremely useful. However the reasoning in DeepSeek has been a great help for debugging issues. For this I am using yek[1] to serialize my repo (--max-size 120k --tokens) and feed it the test error. Wrote a quick script name "askai" so Cursor automatically runs it. Good times! Note: I wrote yek so it might be a little bit of shameless plug! [1] https://github.com/bodo-run/yek

The token estimator of this package is quite inaccurate, since it appears to just take the number of characters, minus whitespace. This can lead to it being overly conservative, which would degrade an LLM's performance. That said, it can be improved in subsequent versions to properly integrate with a model's tokenizer so it can know the true token count. https://github.com/bodo-run/yek/blob/17fe37fbd461a8194ff612e...

Oh totally forgot about homebrew installer. I'll fix it ASAP. Sorry about that. Edit: Working on a fix here https://github.com/bodo-run/yek/pull/14 You can use the bash installer on macOS for now. You can read the installer file before executing it if you're not sure if it is safe