@aishwary07jain · X

fran-mora · HN

I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.

kyisaiah47 · HN

SkillWorks – every Claude Code skill, scored on whether it loads

kirankgollu · HN

Oodle.ai – $10 per million agent traces

@EveryDayFSDev · X

I’m building catch SaaS bugs before your users do: plain-English flows + AI browser automation that adapts to changes and wires straight into CI/CD.

@WebScore_now · X

@KSFirasa · X

Hello! I built a tool that profiles code (python only atm) across 14 dimensions detecting violations and capabilities outputting a full report. A bit more nuanced than "AI-powered insights". Free while in beta. Thank you!

@NEURL_OS · X

Hey we’ve built NEURL-OS, a tool that turns daily habits into data and a weekly capacity score. For founders juggling constant decisions, it helps reveal what’s fueling your focus and output—and what’s quietly draining it. Try it free:

pepperpoppins · HN

Trunchbull, run real models against any benchmark in your browser

@igorluchenkov · X

Hey Yuhao! Been running a lot of agents while building UI and built a tool for visual testing that integrates nicely with agents and gives your agent a way to make sure it didn't introduce any UI regressions:

@uchechukwuevan · X

@GurkaPraveen1 · X

An app helps by tracking ur performance Helps students to track results of particular subject Check out what I just built with Lovable!