@MarwanMaherH · X

@nourdyasein · X

@polsia · X

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

@bestaipacks · X

Qa prompt tool Let's you fix bad ai prompts for free, gives you a score and saves your improved versions. Paid account gets more qa reports, access to better models and ability to re run improved prompts on just about any model

@adib_011 · X

Built RepoLens at the Codex Meetup, an evidence-first JS/TS code review tool that shows reviewers where to look, without executing repository code. Built with Codex + GPT‑5.6. Try it: Demo: @OpenAIDevs @mitul_shahriyar #CodexMeetup

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

shreyans_assistiv · Product Hunt

AskCodi Orchestrate agents at scale while reducing cost

@Ishanv9hj · X

We just launched lumioguard for the verification and monitoring layer for ai native teams with start for free #indidev #indihackers #BuildinPublic

@sunmer575399 · X

找了好久的AI工具，终于被我挖到 star了 1️⃣ 全网最大的开源prompt库，两万多个现成提示词，从写代码到当翻译官都有。我刚拿它的prompt写周报，比之前自己瞎敲的省了半小时。 2️⃣ 它不挑模型，ChatGPT、Claude、Gemini、Llama一套通吃。同一个prompt在GPT-4和Claude上跑出来效果都很稳，不用来回调格式。 3️⃣ 可以自己部署到公司内网，完整隐私保护。我实测docker一键起服务，10分钟搞定，同事拿去用也没说难上手。 开源协议宽松，商用也没问题。 这项目2022年底就上线了，算得上prompt界的祖师爷。 被Forbes报道过，哈佛、哥伦比亚都在引用，还拿了GitHub员工精选。 最夸张的是它的配套书，25+章节从基础到高级推理全讲透，光读完这本就比你自己瞎试几个月强。 你自己写完的prompt也可以传上去共享，同步到GitHub自动生成数据集，白赚一个开源履历。 你们手里攒了哪些超好用的prompt，拿出来分享下？ 🔗 #AI #AI工具老炮

@hyraxai · X

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)

@LaunchGuardHQ · X

I'm an HVAC installer, not a developer. Built LaunchGuard nights & weekends with AI coding tools. It scans AI-built apps for leaked API keys, wide-open databases, and vulnerable dependencies — then opens a real GitHub PR with the fix.