SamInTheShell · HN

My Fable 5 Project Was a Multiraft Database and Blob Store

@mj_jimmi · X

ent101 · HN

The Safe, Production-Ready Backend for AI-Generated Apps

@ashkans_dev · X

An ETL tool:

zxhywork · V2EX

Muse Image AI Meta Superintelligence Labs 7 月 7 号发布了他们第一个图像模型 Muse Image ，内部代号 Mango 。玩了两天，这个模型有几个点确实有意思： - **Agentic 生成**：出图前先规划布局，需要事实的场景会联网搜，画完自查一轮再交稿，长 prompt 一次过的概率明显高 - **图内文字能看了**：海报标题、图表、甚至可扫的二维码都能直接画进图里，这是大部分生图模型至今糊掉的地方 - **多参考图合成**：从几张照片里分别取人脸、服装、产品、背景，融成一张不违和的图 官方入口在 Meta AI App / meta.ai / Instagram Stories ，国内用着别扭，还得装 App 。我就照着上一个站的路子做了个纯网页版：[museimages.io]( https://museimages.io/)。 产品上砍得很狠，只做图像，三个入口： - [Meta Muse Image 在线生成器]( https://museimages.io/ai-image-generator)

chenglong-hn · HN

Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple

@poweroverthink · X

Stop chasing clients for files, copy and feedback. BriefBasket keeps everything in one simple place.

allybahaei · HN

Bring all your sources into a visual space, ask questions with full context, branch LLM conversations, and go deep on YouTube videos / research papers to build your knowledge canvas.

@RedjanHysa · X

App Store Connect makes simple things painful, so I built . Localizing pricing across every available storefront, writing and translating all app's metadata, editing screenshots in one tool and uploading them in another... well, that just takes time from actually building. With MetaRun you have everything in one place: bulk pricing with ppp-based localization, AI-translated metadata, screenshot studio where you edit screenshots, translate them in every language you support and publish them with one click, and many other tools. Oh, you can also use MetaRun directly in Claude Code, Codex, or whatever agent you're using, via MCP, so you never leave your IDE :). Check it out and tell me what you think.

@adhikari_premi · X

@M365Clarity · X

@FalhdirA · X

Check out what I just built with Lovable!