thesysdev/appless

What if your phone had no apps

What it solves

AppLess reimagines the mobile user experience by replacing traditional, static apps and menus with a generative UI operating system. Instead of navigating through installed applications, users simply ask for what they need, and the system generates a custom, interactive native screen on the fly.

How it works

The system uses a specialized model called OUI-1 (served via vLLM) that writes in a compact, streaming-first UI language called "openui-lang". A renderer then converts this language into real native components—using Cupertino for iOS and Material 3 for Android—ensuring the interface feels native to the device. To provide real-world data, the model can call external tools like Exa for web search, while navigation is made seamless through speculative prefetching of likely next screens.

Who it’s for

It is primarily an experimental project for developers and researchers interested in Generative UI, as well as those looking to build a new paradigm of app-less mobile interfaces by integrating real-world APIs into the provided shell.

Highlights

  • Generative Native UI: Screens are streamed live and rendered as native iOS or Android components rather than static JSON or web views.
  • Platform-Aware Rendering: A single model contract allows the same prompt to render differently based on the device's native design system.
  • Speculative Prefetching: Predicts and generates subsequent screens ahead of user interaction to make navigation feel instant.
  • Tool Integration: Supports mid-stream tool calls (e.g., web search) to ground generated content in real-time data.

Related

  • Project
    thesysdev/openui

    OpenUI is a framework‑agnostic, streaming‑first UI library that lets LLMs generate UI components using a compact language (OpenUI Lang). It provides parsers, prompt generators, and runtime bindings for React, Vue, Svelte, Angular, plus a CLI for scaffolding apps. The language reduces token usage by ~50 % versus JSON, enabling progressive rendering of model‑generated interfaces.

  • Project
    AGenUI/AGenUI

    AGenUI is a production-grade SDK that implements Google's A2UI v0.9 protocol to render LLM-generated interactive UI in real time on iOS, Android, and HarmonyOS. A shared C++ core handles parsing, layout, and diffing while native renderers draw the components, giving 22 built-in UI components, custom component registration, Function Call support, a self-contained JSON catalog schema for constraining LLM output, an agent skill for turning natural language into UI protocol messages, and a local Studio workbench for prototyping.

  • Project
    minitap-ai/mobile-use

    An open-source AI agent that automates Android and iOS devices using natural language to perform tasks and scrape data from apps.

  • Project
    vercel-labs/json-render

    json-render is a generative UI framework that lets AI create interfaces from prompts while staying safe and predictable. It works by constraining AI output to a catalog of defined components and actions, which are then rendered across many platforms.

  • Project
    wandb/openui

    An open-source tool that lets you describe UI components in plain language and see them rendered live, with the ability to convert them to React, Svelte, or Web Components.