valknut

I started Valknut (https://github.com/sibyllinesoft/valknut) when I saw the writing on the wall regarding Agent code structure/abstractions/etc being a limiting factor in the ability to autonomously build projects. My experience was that good linters helped, but it wasn't enough, you needed to be able to enforce information-theoretic related organizing principles in addition to file/function LOC and local complexity metrics to guide agents on how to structure code. Originally I tried to walk the line between improved agent performance and human readability, but current models are so good I don't think human readability matters much, though at a high level, being able to grok the overall folder structure still matters. I've got my hands full polishing a demo for my game, but I intend to revisit Valknut by crafting an eval set that lets me

Valknut is pretty good at forcing agents to build more maintainable codebases. It helps them dry out code, separate concerns cohesively and organize complexity. https://github.com/sibyllinesoft/valknut

This is a big part of why vibe coded projects fall over. AI creates big balls of mud because it's myopic as hell. Linters help but they're still pretty limited. I've had good success using https://github.com/sibyllinesoft/valknut to automate the majority of my refactoring work. I still do a style/naming pass on things, but it handles most issues that can be analytically measured.

I have a code quality analysis tool that I use to "un-slopify" AI code. It doesn't handle algorithms and code semantics, which are still the programmer's domain, but it does a pretty good job of forcing agents to dry out code, separate concerns, group code more intelligently and generally write decoupled quasi-functional code. It works quite well with the raph loop to deeply restructure codebases. https://github.com/sibyllinesoft/valknut

I analyzed a lot of repositories when developing Valknut (https://github.com/sibyllinesoft/valknut) in order to eval the algorithms and catch bugs. Since people love leaderboards and I want to support well written open source software, I figured I'd make a little app so people can test their work and optionally show off their score for promotional purposes. TS/JS/Go/Python/Rust are currently supported. If you disagree with scoring, I'm happy to have a conversation and do evals based on your feedback, but keep in mind that the code that is optimal for humans is not quite the same code that's optimal for agents (though there's a lot of crossover!). If there's interest I'm happy to put together a Github badge to let you show off your ranking/score.

Hi y'all, In my work to reduce the amount of time I spend in the agentic development loop, I observed that code structure was one of the biggest determinants in agent task success. Ironically, agents aren't good at structuring code for their own consumption, so left to their own devices purely vibe-coded projects will tend towards dumpster fire status. Agents aren't great at refactoring out of the box either, so rather than resign myself to babysitting refactors to maintain agent performance, I wrote a tool to put agents on rails while refactoring. Another big problem I encountered trying to remove myself from the loop was knowing where to spend my time efficiently when I did dive into the codebase. To combat this I implemented a html report that simplifies identifying high level problem. In many cases you can click from an issue in the r

A quick pass through this repository validates that there is a lot of tech debt in this code too. For a very simple example, consider that the analysis code is doing string searches to attempt to detect various syntatic constructs. https://github.com/sibyllinesoft/valknut/blob/aaf2b818a97b8d...

Official release is tomorrow, I'm just doing final release prep cleanup and getting the product page in order, but the crate/brew formula is in decent shape, just missing some features I'll be shipping soon. https://github.com/sibyllinesoft/valknut if you want to jump the line though.

Looks pretty neat, but I have a vision for my web client that I'm excited to execute on (it's a 3d map that shows all active agents with branching, it has high performance zoom/pan so you can visualize your entire swarm's activity at once, lots of nice visual flash), I just have a jammed launch schedule so I haven't been able to put the time towards the work yet, I'm trying to ship 3 products this week! Speaking of which, if you're interested in a CLI that creates a comprehensive refactoring plan for agents, I'm going to drop https://github.com/sibyllinesoft/valknut tomorrow once I polish the github and create a product page for it on my site. It's helped me keep my agents on rails while refactoring, so that I can scale my AI workflows to larger codebases. It's available on crates as valknut-rs and brew as valknut.