Haven — vibe coding 部署平台，上传 ZIP 或连接 GitHub/Gitee，AI 梳理需求并补齐支付、多用户、日志安全、运维等环节，一天内交付可对外服务的产品

shreyans_assistiv · Product Hunt

AskCodi Orchestrate agents at scale while reducing cost

@_m3rl1n

@LeeLeepenkman · X

nice im working on lots of AI stuff so right now :)

vpetroff · HN

CobaltCode – Dedicated persistent computer for Codex

@ankushKun_ · X

Hi, we're building @use_construct , an autonomous cloud comouter that works for your business.

@vilmire_tmp · X

Tired of alt-tabbing between terminals to check if my coding agents were done, stuck, or waiting on approval. So I built ADHDev: control Claude Code / Codex / Cursor CLI from your browser or phone, on every machine you own. AGPL self-hosted edition too.

jayaprabhakar · HN

I've been building an open source formal methods system (fizzbee.io) for the past few years. Today I'm launching a new app built on the same technology. It performs requirements engineering using formal verification to uncover gaps and produce precise instructions for your coding agents to follow. When given a prompt, it - asks high signal follow-up questions - converts to formal spec and identifies complex requirements gaps - generates validation scenario At the end, it produces a specification document that can be shared with coding agents. In my trials on various projects, it produces working code in fewer iterations. Please give it a try and share your feedback. https://fizzbee.ai/ You can also look at a sample project. https://fizzbee.ai/projects/94bf2869-97a1-445c-8f5d-4445848b...

@edgex11lz · X

@durdom_evm · X

Chinese team at just dropped ZCode 3.0 and it's quietly reshaping the agentic coding landscape while everyone's waiting on Anthropic's roadmap here's what matters: GLM-5.2 is trading blows with Opus 4.8 on the benchmarks that actually count. 81.0 vs 85.0

zhiheng_huang · HN

Sharper – an AI office agent grounded in your knowledge, with citations

davidtsong · HN

Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities