Now in public beta

Give your AI agents
a face.

Weblets are portable, self-contained web apps that AI agents can generate, launch with data, and communicate with. No build step. No dependencies.

my-app/
├── APP.md
├── index.html
└── ...

AI agents are powerful.
But they're trapped in text.

When agents need to show data, visualizations, or interactive tools—they're stuck. Weblets give them a way to create real UI.

🎯

AI-Generatable

Simple enough that any LLM can scaffold a working app in seconds. No complex configs to mess up.

📦

Fully Portable

Just a folder. Zip it, git it, deploy anywhere. No node_modules, no build artifacts.

🚀

Zero Build Step

No webpack. No bundler. No transpiler config hell. Just files that run.

🔧

TypeScript Ready

Use Bun and get native TypeScript support. No compilation step needed.

Three steps to agent-powered UI.

01

Create a weblet

Make a folder with APP.md (manifest) and index.html (entry point). That's the minimum. Add whatever else you need.

02

Agent launches it

The agent serves your weblet and injects context—data, config, a callback channel. Your app reads it on load.

03

Two-way communication

Your UI displays the data, user interacts, and events flow back to the agent. The skill has a brain. Your weblet is its face.

Dead simple integration.

Check if an agent launched you. If yes, use its data. If not, run standalone. That's the whole API.

app.js
// Check if launched by an agent
if (window.__AGENT_CONTEXT__) {
  const { data, emit } = window.__AGENT_CONTEXT__;

  // Render with agent-provided data
  renderDashboard(data.metrics);

  // Send events back to the agent
  button.addEventListener('click', () => {
    emit('export-requested', { format: 'csv' });
  });
} else {
  // No agent? Load demo data, still works
  renderDashboard(DEMO_DATA);
}

Start building in 30 seconds.

Tell your AI assistant to build you a weblet. Point it at the spec. Watch it work.

Build me a weblet that visualizes JSON data as a chart.

Learn by building.