Browse Agents
Task
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.
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. About this task →
27 agents fit this task
10 Official · all Verified · 16 No auth needed · 11 API · 14 MCP · 16 CLI · 1 Extension
Cua
APIOpen-source infrastructure for computer-use agents — virtualized macOS, Linux, and Windows sandboxes, SDKs, and…
Screenpipe
CLI · APIRecords your screen and audio 24/7 locally, then serves that history as searchable context to Claude, Codex and other…
UI-TARS Desktop
CLI · APIByteDance's multimodal GUI agent stack that controls desktop and browser interfaces from natural language using…
Mac Control MCP
MCPNative Swift MCP server with 63 tools for full macOS automation — accessibility tree, Safari/Chrome control, screen…
Desktop Commander MCP
MCPMCP server for full desktop control. Lets AI agents execute shell commands, manage files, edit code with diff patches…
Microsoft UFO
CLIAutomates Windows desktop apps through natural-language tasks with the UFO2 Desktop AgentOS, and orchestrates agents…
Agent S
API · CLIOperates desktop graphical interfaces like a person, combining hierarchical planning with visual grounding to click…
Claude Cowork
APIWorks as an AI coworker in Claude that reads your files, runs scheduled tasks across your apps, and ships finished…
Agent TARS
CLIByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and…
BitFun
CLIRuns an open-source desktop and terminal coding agent that plans, edits, tests, and reviews changes inside real Git…
FIRERPA (lamda)
MCP · APIControls Android devices from an on-device server with UI automation, remote desktop, MITM capture, and built-in Frida…
Chrome DevTools MCP
MCPOfficial Chrome DevTools MCP server. Gives AI coding agents browser debugging — inspect DOM, execute JS, capture…
Firefox DevTools MCP
MCP · CLILets MCP clients automate and debug a local Firefox via WebDriver BiDi: navigate pages, fill forms, inspect network and…
iPhone Use
MCPLets Codex and other coding agents operate a real iPhone over USB through a local MCP server: open apps, read screens…
Mobile MCP
MCP · CLILets agents automate native iOS and Android apps on simulators, emulators, and real devices through one MCP server…
Eigent
CLI · APIRuns a local multi-agent desktop workforce that splits tasks across specialized workers with browser, terminal, and…
Kampala
APIYC W26. Watches one human workflow demo and converts any website, mobile, or desktop app into a stable REST API — no…
ARTEMIS
CLIConverts natural-language instructions into reliable Android device automation for coding agents, capturing logs and…
Ghost OS
MCP · CLILets any MCP-capable agent see and operate every macOS app through the accessibility tree, with vision fallback and…
Browserless
API · MCP · CLIRuns hosted or self-hosted headless browsers for agents and scripts, with REST APIs for screenshots, PDFs, and…
Figma MCP Server
MCPGives coding agents Figma design context, variables, screenshots, and generated code from frames, and lets them write…
Open Interpreter
API · CLILets LLMs run Python, JavaScript, and shell commands locally to summarise PDFs, create charts, control files, and…
Argent
MCP · CLIGives AI coding assistants control of iOS simulators, Android emulators, TVs, and Electron apps to tap, debug, profile…
bigarrow (big-arrow-on-the-screen)
CLILets coding agents draw arrows, boxes, and labels over any macOS window to show the human what to click, with copy…
Page Agent
MCP · ExtensionEmbeds a GUI agent in any web page with one script tag, driving the existing DOM from natural-language instructions…
Safari MCP Server
MCPConnects AI agents to a live Safari window for web debugging: DOM inspection, network monitoring, console logs…
Agent Device
CLI · MCP · APIAutomates iOS, Android, HarmonyOS, TV, macOS, and Linux devices from AI coding agents through a CLI, MCP server, and…