Browse 45 reviewed agents connected to computer-use, GUI, web, and mobile agents. Each entry links to primary evidence and records its scope.
Review means AI-assisted editorial inspection, not independent reproduction. Unknown licenses and specifications remain unknown.
Browser automation agent on the AG2 framework that pairs a planner agent with a browser navigation agent to fill forms, search shops and work through sites, also callable over a local HTTP API.
Release date not recorded · webSimular's open-source framework for computer-use agents that click, type and scroll through desktop and web apps on macOS, Windows and Linux; its third generation, Agent S3, reports 72.6% on OSWorld.
Release date not recorded · desktopMultimodal agent that operates Android apps through taps and swipes without back-end access, building a reusable knowledge base from autonomous exploration or from watching human demonstrations.
Release date not recorded · androidProactive Android agent built on AppAgent that uses GPT-4o to decide whether YouTube or Amazon content would help, operates those apps over ADB, and merges what it finds into its answer.
Release date not recorded · androidMobile agent research using accumulated interaction experience.
Release date not recorded · androidLLM-based assistant for automating work in desktop productivity software by watching the screen and issuing mouse and keyboard commands; its repository says the code will be released later.
Release date not recorded · desktopScreenshot-based mobile agent implementation with training and inference code for chain-of-action prediction.
Release date not recorded · androidLLM-powered Android task automation built on DroidBot, released with DroidTask, a dataset of per-app screenshots, view hierarchies, exploration records and ground-truth task files.
Release date not recorded · androidAn Android automation implementation that builds app documentation from exploration traces and evaluates language-model-generated execution code in emulator workflows.
Release date not recorded · androidWeb navigation agent built on ChatGLM3-6B that simplifies HTML for the model, is trained on hybrid human and AI data with RL and rejection sampling, and comes with the bilingual AutoWebBench.
Release date not recorded · webOpen-source desktop agent that works inside its own Ubuntu Linux virtual desktop, with a web task interface, REST APIs for tasks and direct control, a takeover mode and password-manager logins.
Release date not recorded · desktopScreenshot-driven agent implementation for MiniWoB++ and WebShop, using a visual observer and context-aware prompts to issue mouse and keyboard actions.
Release date not recorded · webResearch implementation combining screen and layout perception with conditional action prediction for smartphone automation.
Release date not recorded · androidResearch demonstration of collaborative Windows GUI automation with dynamic task scheduling and recovery mechanisms.
Release date not recorded · desktop, windowsFramework in which foundation models control games and software from screenshots alone, acting through keyboard and mouse, shown on RDR2, Stardew Valley, Cities: Skylines and Dealer's Life 2.
Release date not recorded · desktopReleased inference and evaluation code for demonstration-conditioned mobile GUI agents on LearnGUI-Offline. The repository describes a multi-agent adaptation method and links the LearnGUI demonstrations.
Release date not recorded · unspecifiedA screenshot-driven browser agent over Chrome DevTools Protocol, with resumable sessions, context compression, action replay and configurable completion checks.
Release date not recorded · webMicrosoft agent application combining orchestration with browser interaction; successor to Magentic UI.
Release date not recorded · webAn Android agent that combines global task planning and memory with a local action executor, using reflection to revise mobile interaction steps.
Release date not recorded · androidAndroid GUI agent that operates real phones through ADB with hierarchical reflection and a multi-agent framework, run from a web interface or Python and evaluated on AndroidWorld and AndroidLab.
Release date not recorded · androidMobile device agent family using visual interface interaction.
Release date not recorded · android, cross-platformAndroid automation component with hierarchical planning, reflection and persistent tips/shortcuts learned across task sequences.
Release date not recorded · androidMobile-control research implementation combining operating-procedure context with human interaction for personalized task execution.
Release date not recorded · androidAn Android client and Python-server agent that learns reusable app subtasks through exploration, selection, derivation and memory recall.
Release date not recorded · androidiOS agent engine organized around an observe, decide, verify and act loop, using WebDriverAgent screen state and phone actions such as taps, typing, swipes and app switches.
Release date not recorded · iosA browser-extension agent that reads pages, interacts with elements and moves between tabs from a side-panel task interface.
Release date not recorded · webAssistant framework combining code execution and computer interaction.
Release date not recorded · desktopPhone agent model and framework with device interaction tooling.
Release date not recorded · android, iosTools for learning and automating workflows from desktop demonstrations.
Release date not recorded · desktopThe OpenAgents browser-control component, connecting a Chrome extension to a web agent and local chat platform for navigating sites and completing interface tasks.
Release date not recorded · webOpen-source library for generalist agents acting on an operating system's web, terminals, files and third-party apps, with the FRIDAY assistant, which takes custom tools and self-learns Excel tasks.
Release date not recorded · desktopAndroid GUI-agent research implementation that uses confidence-guided interaction to choose between autonomous actions and human assistance.
Release date not recorded · androidHuman-cognition-transfer framework for PC agents: PC Tracker logs human computer use, cognition completion turns logs into cognitive trajectories, and a planner works with a grounding agent.
Release date not recorded · desktopMulti-agent desktop automation component for Windows and macOS, combining active perception, task decomposition and reflection for workflows spanning applications.
Release date not recorded · desktop, windows, macosA MiniWoB++ agent that uses explicit and implicit recursive criticism-and-improvement prompts to refine action plans and ground actions to browser state.
Release date not recorded · webEnvironment and agent in which a vision-language model controls real desktops over VNC with mouse and keyboard in plan, act and reflect stages, plus a hand-annotated dataset of daily computer tasks.
Release date not recorded · desktopGeneralist web agent framework for large multimodal models such as GPT-4V, with a Playwright tool that runs agents on live websites, text-choice and set-of-mark grounding, and a crawler mode.
Release date not recorded · webFramework, released in November 2023, in which a multimodal model views the screen and picks mouse and keyboard actions toward a goal, with backends such as GPT-4o, Claude 3, Gemini and LLaVA.
Release date not recorded · desktopSpreadsheet automation agent for Windows/Excel, with benchmark assets and a separately released headless Ubuntu evaluation backend.
Release date not recorded · desktop, windows, linuxDesktop agent that records demonstrations, derives semantic action traces, and uses them to plan and execute related workflows.
Release date not recorded · desktop, windows, macosNext.js and FastAPI playground from Steel for trying web agents in a controlled browser environment, with live views of browser interaction and support for providers such as Claude and GPT-4.
Release date not recorded · webWindows agent framework for application and desktop automation.
Release date not recorded · windows, desktopDesktop app for a local GUI agent driven by UI-TARS and Seed-1.5-VL/1.6 models, offering local and remote operators for computers and browsers; the repository also ships the Agent TARS CLI and web UI.
Release date not recorded · desktop, webAn Android automation implementation that translates screenshot-based UI understanding into language descriptions for step-by-step LLM planning and action execution.
Release date not recorded · androidAndroid phone assistant combining model-driven tool use with accessibility-tree reading, screenshots, and tap, swipe and text-entry primitives. Its documented interaction flow presents operation plans for user confirmation.
Release date not recorded · android