Computer Use

App: Claude Cowork

Anthropic

Featured

Anthropic's desktop agent for non-coding knowledge work: point it at a folder, describe the outcome, and it does the multi-step work itself.

App: Manus

Manus AI

Featured

A general autonomous AI agent that executes multi-step tasks end to end in its own cloud environment.

App: Construct Computer

Construct

Featured

Cloud AI employee with its own Linux desktop that runs multi-step work across Gmail, Notion, Linear, GitHub and Slack.

App: Zinley

Zinley, Inc.

Featured

A personal AI representative with its own phone number, inbox and computer that takes calls, works your email and runs tasks under rules you set.

App: Rindler

Rindler signs in to the web portals your team already uses and finishes the task you describe in a sentence — pulling records, downloading invoices, checking statuses, submitting forms.

App: Browser Use

The open-source library that lets AI agents actually use websites — clicking, typing, and reading like a person.

MCP: Daytona MCP Server

by Daytona

Daytona's official MCP server: give an agent a disposable cloud sandbox with a file system, git, process execution, computer use and a live preview URL.

MCP: nuphus-mcp

by Nuphus Team

Computer use for any MCP client: 36 tools covering screenshots, window control, mouse and keyboard, and Chrome over CDP, with local OCR built in and vision on your own key.

MCP: Peekaboo

by OpenClaw

macOS screen capture and GUI automation over MCP — see the screen, then click, type and navigate it, with local or hosted vision models.

MCP: Windows-MCP

by CursorTouch

Computer-use MCP server for Windows — 19 tools for clicking, typing, shell, filesystem and registry, driving the desktop without a vision model.

MCP: Playwright

by Microsoft

Browser automation for agents — navigate, click, type, and read pages using Playwright's accessibility tree, no screenshots required.