AAswordman/Operit

The most powerful AI agent and AI chat software on Android/Operit是一款Android上能力最为强大、发展最久的AI Agent

What it solves

Operit AI is an open-source AI agent platform for Android that transforms a mobile device into a powerful workstation. It solves the problem of limited AI interaction on mobile by connecting LLMs to system capabilities, a full terminal environment, and web automation tools, allowing users to perform complex tasks like coding, device automation, and information retrieval directly on their phones.

How it works

The platform integrates cloud-based models (OpenAI, Anthropic, Gemini) and local inference engines (MNN, llama.cpp for GGUF models) into a unified interface. It uses tool calling, workflows, and extensions (ToolPkg, MCP, Skills) to interact with the Android system. It provides a built-in Ubuntu 24.04 user space via PRoot, a browser agent for web interaction, and a graph-based memory system for long-term context.

Who it’s for

It is designed for power users, mobile developers, and AI enthusiasts who want a highly customizable, agentic experience on Android, including those who need a full Linux terminal and code editor on the go.

Highlights

  • Deep Android Integration: Automates interfaces via Accessibility, Shizuku, or Root, and includes a built-in browser agent for page interaction.
  • Mobile Development Suite: Features a full Ubuntu 24.04 ARM64 user space, code editor with syntax highlighting, and project templates.
  • Flexible Model Support: Supports cloud APIs, local MNN/GGUF models, and connection to local services like Ollama.
  • Extensible Ecosystem: Includes a unified marketplace for scripts, ToolPkg, Skills, and MCP services, alongside a visual workflow builder.
  • Advanced Memory & Personas: Manages graph-based long-term memory and supports multi-character group chats with independent capabilities.

Related

  • Project
    omnimind-ai/OmniBot

    An on-device AI agent for Android that integrates system-level actions, a local workspace, and an extensible tool ecosystem to execute complex tasks.

  • Project
    yashab-cyber/opendroid

    OpenDroid is an Android app that runs an autonomous AI agent on the phone. It parses natural‑language requests into multi‑step plans, executes actions across system settings, apps, navigation, payments, and smart‑home devices, and verifies results. The app includes an on‑device model manager for LiteRT‑LM models, a vision engine for screen understanding, a four‑tier personal knowledge graph, voice wake‑word support, and a premium Jetpack Compose UI. It supports 13 LLM providers (Gemini, Claude, OpenAI, Ollama, etc.) with automatic fallback. Built with clean architecture, Dagger‑Hilt, Room, and Kotlin, it requires JDK 21 and Android 15 to compile. Licensed under Apache 2.0.

  • Project
    Mangi-11/Eta

    Eta is an Android app that turns a phone into a system‑level AI agent. Users supply their own LLM API key; the built‑in Agent Runtime lets the model call Android APIs, a GUI accessibility agent, a Linux‑style terminal, file tools, a WebView browser, and remote services. It can set alarms, control media, read notifications, run scripts, edit files, and more, with optional root/Xposed integration for deeper system access. Designed for power users and developers who want programmable, cross‑app automation on Android.

  • Project
    Core-Mate/OpenGUI

    OpenGUI is a framework that lets AI agents control real Android phones by interpreting screenshots and issuing UI actions. It provides WorkBuddy and DeepSeek Harness plugins for easy chat‑based use, a full optional backend for advanced task planning, and a small Android client that performs taps, swipes, typing, etc. Ideal for AI‑driven testing, automation, and content creation on mobile devices.

  • 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.