kunchenguid

HTML is the new markdown. Lavish is the new editor for your HTML artifacts.

47
2
100% credibility
Found May 13, 2026 at 61 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
JavaScript
AI Summary

Lavish AXI is a local browser tool that lets people review and annotate AI-generated interactive HTML documents, sending targeted feedback back to the AI for collaborative improvements.

How It Works

1
🧑‍💻 Ask your AI for visuals

You tell your helpful AI to create an interactive document like a plan, diagram, or design mockup.

2
📄 AI makes the file

Your AI generates a special webpage file full of rich visuals and details for you to check.

3
🚀 Open in the editor

With one easy launch, the file opens in your browser as a beautiful, interactive review space.

4
👀 Browse and explore

Wander through the page, seeing diagrams, tables, or designs that make ideas clear at a glance.

5
✏️ Point out changes

Click any part or highlight text to pop up a note box right there, describing exactly what to tweak.

6
💬 Add messages

Queue your notes as colorful reminders and type free messages to guide the AI.

7
📤 Send to AI

Hit send, and all your precise feedback flies back to the AI instantly.

🔄 Loop for perfection

The AI updates the visuals based on your notes, you review again, and together you create something amazing.

Sign up to see the full architecture

6 more

Sign Up Free

Star Growth

See how this repo grew from 61 to 47 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is lavish-axi?

Lavish-axi is a JavaScript CLI that transforms agent-generated HTML files into interactive browser-based review sessions. Tell your agent to output HTML artifacts like diagrams, plans, or prototypes, then run `lavish-axi ` to open a local editor where you annotate elements or selected text and queue precise feedback. Agents poll for changes via `lavish-axi poll `, enabling a tight human-AI loop without screenshots or vague prompts—perfect for HTML GitHub projects, pages, previews, and viewers.

Why is it gaining traction?

It bridges the gap between rich HTML output (think GitHub Pages sites, games, or markdown renderers) and agent collaboration, with precise text-range annotations, element selectors, and auto-injected Tailwind/DaisyUI styling. No cloud dependency, just local long-polling and TOON-optimized AXI responses make it token-efficient for agents. Developers dig the battery-included playbooks for tables, diffs, and comparisons that turn static HTML into editable artifacts.

Who should use this?

Agent users crafting HTML GitHub code, websites, icons, or games who need visual feedback loops. Frontend devs prototyping on GitHub Pages or building HTML markdown editors, parsers, tables, and viewers. Ideal for technical plans, PR reviews, or interactive markdown-to-PDF flows where precise edits beat prose descriptions.

Verdict

Grab it for agent-driven HTML workflows—solid docs and CLI make it dead simple to try on your next GitHub preview. At 47 stars and 1.0% credibility, it's early but mature enough for local use; watch for broader adoption as agent HTML tools proliferate.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.