Agent Switchboard

I need to control a desktop computer

Agents that see the screen and work the mouse and keyboard on a desktop, the way a person does.

27 tools · 10 official

Picked from listings that mention computer use, desktop, mouse or screen in their name, description, tags or skills; those in Browser & Computer Use, or with API or MCP access, rank higher.

Best fits · 12

Cua
API
Open-source infrastructure for computer-use agents — virtualized macOS, Linux, and Windows sandboxes, SDKs, and…
Verifiedby trycua · Browser & Computer Use · 3 skills · API Key
Why Desktop Control: Give AI agents full GUI control over desktop apps, browsers, and system interfaces in sandboxes
Screenpipe
CLI · API
Records your screen and audio 24/7 locally, then serves that history as searchable context to Claude, Codex and other…
VerifiedFeaturedby Screenpipe · Memory & State, Browser & Computer Use · 3 skills · No auth
Why Continuous Screen Capture: Records screen and microphone continuously on-device, storing frames and transcripts locally without sending data to a…
UI-TARS Desktop
CLI · API
ByteDance's multimodal GUI agent stack that controls desktop and browser interfaces from natural language using…
VerifiedOfficialby ByteDance · Browser & Computer Use · API Key
Mac Control MCP
MCP
Native Swift MCP server with 63 tools for full macOS automation — accessibility tree, Safari/Chrome control, screen…
Verifiedby AdelElo · Browser & Computer Use · 4 skills · No auth
Why Screen Capture & OCR: Capture screenshots and extract text from any screen region using native macOS OCR engine
Desktop Commander MCP
MCP
MCP server for full desktop control. Lets AI agents execute shell commands, manage files, edit code with diff patches…
Verifiedby wonderwhy-er · Browser & Computer Use · 5 skills · No auth
Microsoft UFO
CLI
Automates Windows desktop apps through natural-language tasks with the UFO2 Desktop AgentOS, and orchestrates agents…
VerifiedOfficialby Microsoft · Browser & Computer Use, Autonomous Agents · 4 skills · No auth
Why Windows Desktop Automation: Completes multi-app Windows tasks from a natural-language request using a HostAgent and AppAgents, launched with python…
Agent S
API · CLI
Operates desktop graphical interfaces like a person, combining hierarchical planning with visual grounding to click…
Verifiedby Simular AI · Browser & Computer Use, Orchestration · 3 skills · API Key
Why GUI Grounding: Locates on-screen interface elements from a screenshot and maps them to precise click and type coordinates.
Claude Cowork
API
Works as an AI coworker in Claude that reads your files, runs scheduled tasks across your apps, and ships finished…
VerifiedOfficialby Anthropic · Autonomous Agents, Browser & Computer Use · 3 skills · OAuth 2.0
Why Computer Use (Dispatch): Operates applications directly via Dispatch computer use to carry out tasks that need real UI interaction.
Agent TARS
CLI
ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and…
VerifiedOfficialby ByteDance · Browser & Computer Use, Infrastructure & Ops · 4 skills · No auth
Why GUI Control: Control desktop application interfaces using vision-based element detection, clicking, and keyboard input.
BitFun
CLI
Runs an open-source desktop and terminal coding agent that plans, edits, tests, and reviews changes inside real Git…
Verifiedby GCWing · Code & DevTools, Browser & Computer Use · 3 skills · API Key
Why Repository Delivery: Plans, edits, tests, and commits changes inside real Git repositories using desktop or terminal interfaces.
FIRERPA (lamda)
MCP · API
Controls Android devices from an on-device server with UI automation, remote desktop, MITM capture, and built-in Frida…
Verifiedby firerpa · Browser & Computer Use · 5 skills · No auth
Why Remote Desktop: Streams and controls the device from a browser with multi-user access.
Chrome DevTools MCP
MCP
Official Chrome DevTools MCP server. Gives AI coding agents browser debugging — inspect DOM, execute JS, capture…
VerifiedOfficialby Chrome DevTools · Browser & Computer Use · 4 skills · No auth
Why Screenshot Capture: Take full-page or viewport screenshots and return them to the agent for visual inspection

See all 27 on Browse, with filters

Official · 10

The ones published by the company behind the product.

See all 10 official on Browse

In stacks

Ship iPhone and Android apps from one coding agentWith iPhone Use, among 4 tools that work together.

Missing a tool that does this? Suggest a listing.

/tasks/control-a-computer

I need to control a desktop computer · 27 fit · 10 official · keywords: computer use, desktop, mouse, screen · categories: browser-computer · access: api+mcp

Agents that see the screen and work the mouse and keyboard on a desktop, the way a person does.

best fits

cuaapiDesktop Control: Give AI agents full GUI control over desktop apps, browsers, and system interfaces in sandboxes screenpipecli+apiContinuous Screen Capture: Records screen and microphone continuously on-device, storing frames and transcripts locally without sending data to a…ui-tars-desktopcli+apiByteDance's multimodal GUI agent stack that controls desktop and browser interfaces from natural language using vision-based grounding.mac-control-mcpmcpScreen Capture & OCR: Capture screenshots and extract text from any screen region using native macOS OCR engine desktop-commander-mcpmcpMCP server for full desktop control. Lets AI agents execute shell commands, manage files, edit code with diff patches, and run long processes with live output streaming.microsoft-ufocliWindows Desktop Automation: Completes multi-app Windows tasks from a natural-language request using a HostAgent and AppAgents, launched with python…agent-sapi+cliGUI Grounding: Locates on-screen interface elements from a screenshot and maps them to precise click and type coordinates.claude-coworkapiComputer Use (Dispatch): Operates applications directly via Dispatch computer use to carry out tasks that need real UI interaction.agent-tarscliGUI Control: Control desktop application interfaces using vision-based element detection, clicking, and keyboard input.bitfuncliRepository Delivery: Plans, edits, tests, and commits changes inside real Git repositories using desktop or terminal interfaces.firerpamcp+apiRemote Desktop: Streams and controls the device from a browser with multi-user access.chrome-devtools-mcpmcpScreenshot Capture: Take full-page or viewport screenshots and return them to the agent for visual inspection

official

ui-tars-desktop, microsoft-ufo, claude-cowork, agent-tars, chrome-devtools-mcp, firefox-devtools-mcp, artemis, figma-mcp-server, page-agent, safari-mcp

related tasks

/tasks/automate-a-browser37 fitautomate a browser /tasks/search-the-web27 fitsearch the web /tasks/scrape-websites20 fitscrape websites

in stacks

/stacks/iphone-and-android-appsiphone-useShip iPhone and Android apps from one coding agent

more

/browse?task=control-a-computerall 27, with filters /tasksevery task /api/tasks/control-a-computerthis task as JSONGET · no auth