AARE

ARTEMIS is an open-source Google tool for natural-language Android automation and testing. It drives real phones or emulators through end-to-end workflows, generates test plans, captures screenshots and logs, profiles performance, and produces structured reports. Its element-locating system combines accessibility hierarchies and OCR with visual-model and coordinate fallbacks for custom interfaces. ARTEMIS provides a CLI, web visual console, Python SDK, and native Model Context Protocol (MCP) server for connecting Android devices to AI coding assistants such as Antigravity, Claude Code, Codex, and Windsurf. Its Flash profile uses a reactive observe-and-act loop with compressed history, while the Pro profile uses planning, pre-execution checks, action bursts, incident recovery, checkpoint verification, and optional final reports. The project also includes an accessibility helper for reading screen layouts and can fall back to UIAutomator2. It is distributed under the Apache License 2.0; the repository reports 99%+ completion on Google Research's AndroidWorld benchmark.

FIRERPA is an Android device-control and automation platform whose server runs on the device and is orchestrated through a Python client. It combines browser-based remote desktop and live streaming, selector-based UI automation, OCR and image matching, packet capture and MITM, Frida-based instrumentation, proxy/VPN/frp/P2P networking, ADB and SSH, system controls, and multi-device management through a unified service and API. Its automation model supports UI selectors, watchers that react to matching UI changes, virtual displays for background automation, multi-touch recording and replay, and OCR backends including PaddleOCR, EasyOCR, and custom HTTP services. The platform also exposes an MCP server and a natural-language agent that can call tools through OpenAI-compatible APIs, while its Python API covers device operations, networking, files, processes, settings, and runtime metrics. The repository documents deployment through an Android app, Magisk module, manual extraction, or ROM integration, with operation on rooted or non-rooted devices and support for physical devices, emulators, cloud phones, and multiple CPU architectures. Its remote desktop supports MJPEG, H.264, and WebRTC, with TLS, certificate access control, browser-based file and terminal functions, and optional multi-user access. The repository provides documentation and identifies device-farm.com as its homepage.

Escrcpy is an open-source graphical interface for displaying and controlling Android devices through the scrcpy engine. It provides an embedded mirror with screen-fitting and orientation handling, configurable mappings for touch, joystick, swipe, scrolling, and automation, simultaneous control of multiple devices with broadcast input, batch screenshots and APK installation, and a draggable control bar for device operations. It also supports wireless ADB connections with LAN discovery and Gnirehtet reverse tethering, visual step-by-step automation with screen-image recognition, global shortcuts, and an MCP-based AI assistant with multi-model chat. Released packages are available for manual installation, with macOS installation through Homebrew; advanced features from the private EscrcpyX extension are paid, and the project states that updates are irregular.

CarWatch is an open-source, offline in-car AI agent from ThinkOffApp that runs on a Raspberry Pi 5 with a locally hosted language model. It joins chat rooms as a vehicle agent, answers questions from the car's owner's manual using lexical retrieval-augmented generation and page citations, and reads live vehicle and system data while stating when information cannot be sensed. A continuous energy-based voice listener and whisper.cpp provide local speech input without a wake word, with responses played through the car's speakers. The system can monitor OBD and engine data, send departure and arrival messages, trip summaries, and dashcam clips, and expose a phone dashboard for approvals, replies, model selection, and maintenance. The repository describes systemd-managed services for the model server, room agent, voice listener, dashboard, and engine watcher, with Python standard-library code and no cloud subscription required.

HiLight Studio is an experimental Android application by Dhananjay Bhosale for controlling the eight-LED HiLight array on Pixel 11 Pro, Pixel 11 Pro XL, and Pixel 11 Pro Fold devices running Android 17. It supports solid colors, animated patterns, per-app foreground and notification rules, per-contact colors, presets, wallpaper-derived colors, camera and microphone activity rules, face-down notification behavior, quiet hours, and battery-related controls. The app requires privileged access to Android's lights service and can obtain it through root, Shizuku, or ADB. It is installed as a signed APK through ADB, uses notification access for LED alerts, and includes renderer diagnostics and cleanup handling. The project describes itself as experimental and unaffiliated with Google; the videos also state that it operates without internet or contacts permission and applies brightness and duration limits.