Overview

Build custom apps that run inside webAI — with access to on-device AI, real-time collaboration, identity, and encryption APIs.

webAI isn’t just an application — it’s a platform. You can build your own tools, utilities, and collaborative experiences that run as first-class apps inside the webAI shell. Your apps get access to the same APIs that power the built-in apps: local AI inference, peer-to-peer collaboration, user identity, end-to-end encryption, and navigation.

No server required. No API keys. Everything runs on-device.

What you can build

AI-powered tools

Build apps that run AI inference locally — summarizers, writing assistants, code generators, analyzers — all private, all offline-capable.

Collaborative apps

Create real-time multiplayer experiences. The platform handles networking, state sync, and conflict resolution via CRDTs.

Standalone utilities

Dashboards, calculators, games, note-taking tools — anything that runs as a web page can run as a webAI app.

How it works

Apps are single HTML files that run inside a sandboxed iframe within the webAI shell. The shell injects a frozen bridge object — window.apogeeSDK — into your app’s environment, exposing platform capabilities as domain-specific facades.

webAI Shell (Apogee)

Your App (iframe)

window.apogeeSDK

sdk.intelligence → AIsdk.shell → Navigationsdk.messaging / sdk.room → P2Psdk.identity → Identitysdk.crypto → End-to-end encryption

Platform APIs at a glance

Capability	Purpose	Facades
Intelligence	On-device and cloud AI inference	sdk.intelligence
Collaboration APIs	Peer-to-peer spaces, chat, shared state, file sharing	sdk.room, sdk.messaging, sdk.canvas, sdk.files
Identity & Encryption	Device identity (ODID) and end-to-end encryption	sdk.identity, sdk.crypto
Navigation	Shell navigation, recents, projects, title bar slots	sdk.shell
webAI SDK	Bridge object overview and shell manifest declaration	window.apogeeSDK

Start building

1. Understand the app model

   Learn how apps run inside the webAI shell, what constraints apply, and how to structure your project.

   App architecture →

2. Access platform APIs

   Learn the universal pattern for safely accessing shell-injected globals from your app code.

   Accessing shell APIs →

3. Add AI to your app

   Use the intelligence facade to stream completions, manage backends, and inspect runtime state.

   Intelligence reference →

4. Build, bundle, and deploy

   Package your app as a single HTML file and upload it to the webAI launcher.

   App lifecycle →

You don’t need to use every API. Most apps start as standalone tools using just the AI runtime. Add collaboration, identity, or encryption as your app grows.