EmDash hits Astro, Cloudflare for agents

// 55d agoOPENSOURCE RELEASE

EmDash hits Astro, Cloudflare for agents

ANNOUNCEMENT PRODUCT GITHUB PRODUCT HUNT YOUTUBE

EmDash is a full-stack TypeScript CMS built on Astro and Cloudflare, featuring sandboxed plugin isolates and a built-in MCP server. It provides a modern, serverless, and AI-ready successor to WordPress for developer-first content management.

// ANALYSIS

EmDash is a bold attempt to fix the security and extensibility issues of WordPress by using Cloudflare's serverless infrastructure and a sandboxed plugin model.

–Sandboxed plugins in Cloudflare Worker isolates prevent malicious code from compromising the site or database.
–Built-in MCP server allows AI agents like Claude to directly manage and edit site content and schema.
–Built on Astro 6.0, leveraging Live Collections for real-time updates without full site rebuilds.
–Uses Portable Text (JSON) instead of HTML for easier multi-platform rendering across web, mobile, and email.
–Open-source (MIT) and designed for portability, though optimized for Cloudflare D1/R2.

// TAGS

emdashmcpai-codingagentopen-sourcedevtoolcloud

DISCOVERED

55d ago

2026-04-02

PUBLISHED

55d ago

2026-04-02

RELEVANCE

8/ 10

AUTHOR

Github Awesome

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE5h ago

Cursor adds dedicated subagents for skills

Cursor now allows developers to execute tool-heavy or research-intensive agent skills within dedicated subagents. This architectural shift isolates noisy background tasks, keeping the main chat context clean and focused.

UPDATE5h ago

YouTube moves AI labels to video player

YouTube is moving its AI content disclosures from video descriptions to more prominent placements beneath the player and on Shorts overlays. Starting in May, the platform will use internal signals to automatically label photorealistic AI content that creators fail to disclose.

OPEN SOURCE9h ago

Taste Skill kills AI "frontend slop"

Taste-Skill is an open-source framework that provides portable "agent skills" to enforce high-end design principles in AI-generated code. By injecting specific design directives and "anti-slop" rules, it enables LLMs to produce editorial-grade UIs that bypass generic, boilerplate-heavy AI templates.