ephraimduncan · HN

Observability for Coding Agents and LLM Applications

@deduction_find · X

@AnilBatra · X

@KatiyarSaiyam · X

just shipped my first full-stack app 🏠 properties, tenants, rent tracking & maintenance logs, all in one place. UI is still a work in progress — actively making it better. would love honest reviews & UI suggestions! 🔗 #buildinpublic #webdev #reactjs

@marcus_b1973 · X

Honest AI panel validates your idea before you build it.

@Dev_code_04 · X

sailrock · HN

Greenflash – we read every conversation your AI agent has with users

AI Codereview for Gitlab — 基于大模型(DeepSeek,OpenAI等)的 GitLab 自动代码审查工具；支持钉钉/企业微信/飞书推送消息和生成日报；支持Docker部署；可视化 Dashboard - [查看仓库](https://github.com/sunmh207/AI-Codereview-Gitlab)

@ronchampio · 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.

@nathanghart · X

Submitting for approval. I built a free tool for anyone about to ship a vibecoded app. It scans your repo for what bites you in prod (leaked keys, no auth, no error handling). I ran it on 1,868 AI-built apps and even caught my own scanner being ~42% wrong.

@joffreyio · X