{
  "listings": [
    {
      "slug": "autocua",
      "name": "AutoCua",
      "company": "Ashish Yadav and contributors (ComputerUseAgent on GitHub)",
      "grade": "D",
      "fit": "caveat",
      "why": "Takes a goal in words on macOS, Windows or Linux, saves the chat with screens, and sends no telemetry. But it clicks the affirmative on macOS permission dialogs, lets the model answer UAC prompts, documents no VM setup, and acc-23 found Telegram control open to any chat until 4 November.",
      "source": "https://github.com/ComputerUseAgent/AutoCua/blob/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/autocua"
    },
    {
      "slug": "mage-vl-cowork",
      "name": "Mage-VL-Cowork",
      "company": "Microsoft",
      "grade": "C",
      "fit": "caveat",
      "why": "66.0 per cent on 361 OSWorld-Verified tasks in 50 steps (Microsoft's two-run average), and the card mandates a disposable sandbox. The reference harness asks before nothing (the card tells deployers to add confirmation), loading needs trust_remote_code and BF16 on one GPU, and acc-41 found no FP8 build.",
      "source": "https://huggingface.co/microsoft/Mage-VL-Cowork/raw/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mage-vl-cowork"
    },
    {
      "slug": "automation-anywhere",
      "name": "Automation Anywhere",
      "company": "Automation Anywhere, Inc.",
      "grade": "D",
      "fit": "unchecked",
      "why": "The pages read don't describe an open-ended screen agent; AI Agent Studio is listed as an API group but wasn't read.",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/automation-anywhere"
    },
    {
      "slug": "uipath",
      "name": "UiPath",
      "company": "UiPath Inc.",
      "grade": "B",
      "fit": "unchecked",
      "why": "The MCP and agent pages read don't describe an open-ended screen agent an outside agent can hand a goal; UiPath's Studio agent functions weren't read.",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/uipath"
    },
    {
      "slug": "aura-autopilot",
      "name": "Aura Autopilot",
      "company": "TribeVR Inc. (named in Aura's terms of service and privacy policy), trading as Ramen",
      "grade": "C",
      "fit": "no",
      "why": "Plays games in Unreal, Unity, Godot or Roblox editors through engine plugins; it doesn't operate other desktop apps.",
      "source": "https://raw.githubusercontent.com/ramenvr/autopilot/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/aura-autopilot"
    },
    {
      "slug": "autohotkey",
      "name": "AutoHotkey",
      "company": "AutoHotkey Foundation LLC",
      "grade": "C",
      "fit": "no",
      "why": "No model or screen-reading agent; it runs scripts an agent writes.",
      "source": "https://github.com/AutoHotkey/AutoHotkeyDocs/blob/v2/docs/Scripts.htm",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/autohotkey"
    },
    {
      "slug": "autoit",
      "name": "AutoIt",
      "company": "AutoIt Consulting Ltd",
      "grade": "D",
      "fit": "no",
      "why": "No model or screen-reading agent; it runs scripts an agent writes.",
      "source": "https://www.autoitscript.com/autoit3/docs/intro/running.htm",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/autoit"
    },
    {
      "slug": "beam-win",
      "name": "Beam (beam.win)",
      "company": "Noats, Inc.",
      "grade": "F",
      "fit": "no",
      "why": "Beam shares a Mac window with a person at another Mac; llms.txt lists no API, MCP server, CLI or scripting interface an agent could call.",
      "source": "https://beam.win/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/beam-win"
    },
    {
      "slug": "robocorp",
      "name": "Robocorp",
      "company": "Sema4.ai (full legal name not confirmed)",
      "grade": "B",
      "fit": "no",
      "why": "Libraries for scripted automation; no goal-driven screen agent or vision model.",
      "source": "https://rpaframework.org/libraries/windows/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/robocorp"
    },
    {
      "slug": "robot-framework",
      "name": "Robot Framework",
      "company": "Robot Framework ry (Robot Framework Foundation), business ID 2754775-1, Helsinki",
      "grade": "BB",
      "fit": "no",
      "why": "No model or goal-driven agent; it runs keyword suites.",
      "source": "https://robotframework.org/robotframework/latest/RobotFrameworkUserGuide.html",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/robot-framework"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 7,
    "after": [
      "human-in-the-loop.screen-handoff",
      "human-in-the-loop.approve-action"
    ],
    "area": "developer",
    "asks": [
      "set up this app for me",
      "do this on my computer",
      "install and configure the VPN client"
    ],
    "before": [],
    "blockers": [
      "remote-control channel open to anyone who finds it",
      "model weights need remote code or a full-precision GPU",
      "headless or virtual display detected by the app"
    ],
    "capabilities": [
      "desktop.control",
      "desktop.scripting",
      "model.open-weights",
      "agent.run"
    ],
    "category": "desktop-automation",
    "categoryName": "Desktop \u0026 mobile app control",
    "checked": "2026-11-15",
    "companies": {
      "fit": 0,
      "fitWithLimit": 2,
      "tagged": 103
    },
    "competition": "none",
    "fits": null,
    "fitsWithLimit": [
      "autocua",
      "mage-vl-cowork"
    ],
    "id": "desktop-automation.screen-agent-task",
    "listings": {
      "caveat": 2,
      "no": 6,
      "notRead": 3,
      "tagged": 174,
      "unchecked": 2,
      "yes": 0
    },
    "name": "Hand a screen-reading agent an open-ended task on a computer",
    "status": "draft",
    "success": "The goal's end state is visible on screen or in files, the agent stops and asks before irreversible or credentialled steps, and every action is logged with its screenshot. Measured: a 20-step office task completes in under 15 minutes.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/desktop-automation.screen-agent-task.json",
    "weight": 12,
    "weightBasis": "7 of 45 accounts (AutoCua, Mage-VL-Cowork, Pig and Cua threads); demand is clear, completed outcomes are rare in the accounts"
  }
}
