Easy UI Canvas

Author: karlarso · Apache-2.0

English | 简体中文

Online demo

⚠️ No authentication: use it on this machine or on a network you trust only.

Deploying? Hand DEPLOY.md to your AI assistant.

🚀 Deploy in one step

Which prompt do you need? Use the first if Easy UI Canvas is not on this machine yet. Use the second if it is already running — the list page is up — and you want an assistant to use that instance. The assistant reads the Agent guide on the list (/agent.md). It does not install a usage skill.

Not installed yet. Give your AI assistant (Claude Code, Cursor, Codex, …) this sentence. It will read DEPLOY.md, interview you about the details (bind address, autostart, ports, data location, optional export) and deploy it only after you confirm the plan.

Read https://raw.githubusercontent.com/karlarso/easy-ui-canvas/main/DEPLOY.md and deploy Easy UI Canvas by following it. Ask me about the bind address and autostart before you change anything.

The default is local-only (127.0.0.1); the assistant must warn you before it opens anything to your network, because the tool has no login. Chinese version: DEPLOY.zh-CN.md.

Already running. Give the assistant this sentence. It finds the list you already have open, fetches /agent.md from that list’s origin (a Tailscale address and a LAN address are the same list), and follows it. It does not install a skill, and it does not change the bind address, autostart, ports, data location or existing canvases. Chinese version: README.zh-CN.md.

Easy UI Canvas is already running. Do not redeploy it, and do not change its bind address, autostart, ports or data location. Do not install a skill.
Find the running list (the page I have open, or the list URL I give you). Fetch /agent.md and follow it. Keep the list's host (Tailscale, LAN or loopback); do not rewrite it to 127.0.0.1 unless that is the host I gave you. Add ?lang=en or ?lang=zh to force the language. Then tell me you can use this list.

🎨 What it is

A small local web canvas for exploring UI designs: put several HTML screens (frames) side by side on a zoomable, pannable board, comment on individual elements, click through flows on a phone, and let an AI coding agent read and answer the comments in the next session. It runs on your machine and needs only the Python 3 standard library. A running list serves an Agent guide at /agent.md. Everyday use is to fetch that page. Deploy stays DEPLOY.md.

✨ Why use it

• 🔌 Works with any AI coding tool. Any assistant that can read files and run commands (Claude Code, Cursor, Codex and others) can use it, so you can switch tools or models without switching canvas.