SummaGraph — AI 信息图生成工具，粘贴任意形式的文本即可一键生成高质量信息图，内置 20 种视觉风格 × 20 种布局模板，支持系列模式一次生成多页风格连续的信息图，覆盖中英日韩等 9 种语言

@CXSPOC · X

Here you go: - a free tool to create customer journey maps. Built it because there isn't any real solution to create those maps for free and fast.

Midjourney 样式代码库 — SrefHunter 汇集各种社交媒体平台的 Midjourney 样式代码

@ffteema · X

@SpalaAi · X

@moxypixy15683 · X

Are you vibe coding and want to understand the argent language better? understands .ag files. You can pay with kaspa to use it :)

@_heysumit · X

Just shipped an interactive world explorer. watch empires rise, discover notable historical figures, and explore ancient places. live: #buildinpublic #nextjs #webdev #ai

Midjourney Sref code 精选库 — 在 Midjourney 的 prompt 输入 `--sref xxx` ，可以固定生成某种特定风格的图片。这对很多人来说非常方便，不用写一堆效果词，只要记住几位数字就可以。但 `--sref xxx` 有大概 40 亿个，其中重复或者质量不佳的不在少数。因此做了一个网站把一些个人觉得不错的 sref code 收集起来并进行分类，方便新人或

@vkuoo · X

Added more demos showcasing graph-math relationships, built with Codex.

aiobe · HN

I built Commonplace because I wanted to learn more about Google's Open Knowledge Format for knowledge sharing with human and agents. At the same time, Atlassian announced it will start using customer cloud data to train its AI models (opt-out is Enterprise-only), which made a self-hosted Confluence alternative feel timely. The idea: - Use a Git repository that follows Open Knowledge Format with plain Markdown - Commonplace is just a stateless frontend on top (nice UI, but no database, no backups

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

@agenticearth · X