Artifact Viewing Hub

Read AI agent output from local and remote machines in your browser

Problem

Running multiple agents across multiple projects leaves Markdown, HTML, PDFs, code and images scattered across directories and machines. VS Code preview often fails, Claude Artifacts is limited, and T3Code means constant switching. Just reading what the agent produced becomes a chore.

Solution

A self-hosted web app that connects to local folders or remote machines over SSH, lists project trees, renders common file formats inline, and supports Git status, tabs and auto-refresh, so developers can read agent output from anywhere.

Users

Developers and indie creators running multiple AI agents with projects spread across local machines, servers and VPS

MVP

Connect to local and SSH remote folders; render md, html, pdf, images, code, csv; multi-project tabs with auto-refresh; one-command Docker Compose deploy; dark mode and mobile layout

Revenue

Open-core with a paid team plan: multi-user permissions, audit logs and SSO at $5-$8 per seat per month

Why now

AI is shifting developer output from plain code to rich text and web pages, yet preview tools were never designed for that. A dedicated reading layer is a timely gap.