@suhaaspk · X

Hi! building Jungle ( Its a way for small teams to automatically triage bugs and feature requests to keep development moving while they sleep

@oldagencydev · X

Is this still an open offer?😂I'm launching and trying to get it out there. Free no-signup security scans of any URL to catch everything including vibe-coded app issues. Then paid plans for everything up to enterprise! Already using at my other company!

@discorev · X

I've been working on - Using gpt-5.6-sol and Fable in Claude Code via CLIProxyAPI. I've found using these two together with Claude Code Workflows is a killer combination

@simranrambles

potatopotaro · HN

Hacker News minus the slop

@polsia · X

Vibe-coded apps ship by lunch, leak credentials by dinner. Patchmind opens the PR before the founder posts 'just shipped.'

logphase · HN

I've always struggled to hold a large PR in my head. AI-assisted coding has made it worse. Especially when dozens of files are modified, it became harder to understand what changed: distinguishing important changes from trivial ones and identifying if regressions were introduced. I was also tired of switching between file and method to build the whole picture in my head — I wanted all the context at the point of the function I was reviewing. I guess I'm just more of a visual person. I realized t

@GroundedIQ · X

GroundedIQ exists to close the gap between what a client asks for and what actually gets built. That gap is where projects bleed — in change orders, blown timelines, and the slow erosion of trust between a consulting team and the people who hired them.

Antihero5759 · HN

I built a rubber duck chat that you can use through the browser but it's also OpenAI api compatible so you can plugin it in and use it through your favorite ai app. https://bearjcc-quack-language-model.hf.space/

Loerei · HN

I found that describing where a broken UI is and taking screenshots for AI agents really sucks. I’m too lazy to explain an indescribable visual bug or capture a millisecond-long flash. I also don’t want to remember which file defines an element, whether it's right in the .tsx or a problem with the Parent Styles in .css. And even if you can point out the exact file, your agent still has to dig through thousands of lines of code to know what on earth you're yapping about. In a 7700-file monorepo like Cal.com, simply giving the right file in the prompt for your agent saves about 68.9% of execution time and 94.2% of the tokens your agent needs to digest. HoverSource gives all the needed information and further pushes it to -88.5% time and -94.5% tokens, basically skipping the entire digging session and jumping straight to reasoning and executing. The save is linear to how big your codebase is. I want to save tokens, but don’t want to spend my time and energy digging manually, and a junio

dobby_lee · HN

Open-Source for AI tool status checker

@nourdyasein · X