Best AI agents for controlling a computer (2026)
Agents that see the screen and use the mouse and keyboard to work across desktop apps. We list 62 tools for controlling a computer below, each with a link-checked page, pricing as the maker states it and alternatives.
Updated
62 tools: 45 open source, 4 source-available, 10 free or freemium, 1 paid, usage-based or enterprise, 2 pricing on the maker's site.
Memory (8)
Bops
Bops, from Orgo, is a Mac app for a team of AI bots that handle business ops such as inbox triage, CRM follow-ups, invoices and reports, each with its own cloud computer, email address, phone number and shared memory.
Added
Dodaios
Open-source desktop agent OS for Windows, macOS and Linux (formerly Personal Jarvis): talk to it and it runs your coding CLIs side by side, your browser and your apps, with offline Whisper speech, a local wiki memory and support for Ollama, Claude or ChatGPT subscriptions.
Added
TecAdRise Bot
TecAdRise Bot is a free, MIT-licensed Windows desktop app (Electron and Cursor SDK) for running a local team of AI agents, each with its own model, memory, skills, MCP servers, workspace and schedule.
Added
AIOS
Research AI agent operating system that handles scheduling, context switching, memory, storage and tool management for LLM-based agents.
Added
Jarvis
Private, local-first desktop AI assistant with voice and text chat, personal memory, dictation and MCP tools.
Added
MemOS
Memory operating system for LLMs and agents with persistent memory and retrieval.
Added
AirJelly
Always-on desktop assistant that watches your workflow, remembers context and acts proactively.
Added
Anchor Action Index
Shared memory of web workflows for Anchor's cloud browsers: computer-use agents replay proven paths as deterministic code and the model only steps in where a page has changed, exposed as tools on Anchor's MCP server and REST API.
Added
Browser automation (7)
AgentBay
Alibaba Cloud's cloud sandbox service for agents, offering ready-made browser, Linux and Windows desktop, mobile and code environments that agents control through an SDK or MCP.
Added
Skales
Personal AI agent for desktop and mobile that codes, automates the desktop and browser and runs scheduled tasks with local or cloud models.
Added
Ui.Vision RPA
Browser and desktop automation extension with OCR and image recognition, plus an MCP server so AI agents can create and run macros.
Added
Terminator
Desktop automation library and MCP server that lets AI assistants control any Windows app through the accessibility tree, like Playwright for the desktop.
Added
Orke
BOMTOBE's free desktop workspace for Claude Code, Codex and other coding agents: terminal sessions, an in-app browser the agent can use, a Git review window and scheduled AI employees.
Added
UI-TARS-desktop
ByteDance's open-source multimodal agent stack, including a desktop app and Agent TARS for controlling computers and browsers.
Added
OpenSwarm
AI-first 'operating system' where swarms of agents run apps and browsers in parallel.
Added
MCP servers (3)
Windows-MCP
Lightweight MCP server for computer use on Windows that lets agents navigate files, control apps and interact with the UI.
Added
NitroStack
TypeScript framework with decorators and dependency injection for building, testing and deploying MCP servers and MCP apps, with a companion desktop studio.
Added
Next AI Draw.io
Create and edit draw.io diagrams by chatting with AI, as a web app, desktop app or MCP server.
Added
More tools (44)
LCU
Brings the computer-use runtime from the ChatGPT desktop app to Claude Code, Codex CLI and Pi, so any agent harness can see and control your desktop without a Codex sign-in.
Added
Lody
A team workspace for running AI coding agents in parallel in isolated Git worktrees, with live diff review, GitHub integration and access from phone or desktop.
Added
Andee
Andee is an Android agent you install as one APK (Android 11+, no root) that reads the screen and taps, types and replies in any app for you, keeps private on-device notes, and uses the OpenAI-compatible model and speech provider you choose.
Added
Cloudroom
Cloudroom runs Claude Code, Codex, Pi and other coding agents in the cloud, each in its own isolated sandbox on its own Git branch, using your own model logins; the Rust core is open source to self-host, and a desktop app manages local and cloud agents.
Added
Muxin
Muxin is a free, open-source desktop app that puts all your Macs, Linux, Windows and cloud machines in one window, so you can run Claude Code, Codex and other agent CLIs on any of them, see their screens and logs, and take changes to a pull request.
Added
OpenGCUA
Open stack from Tongyi Lab's MAI-UI team for generalist computer-use agents that combine GUI clicks, accessibility trees, terminal commands, APIs and code: an OSWorld harness, a macOS real-device harness, a cross-device SDK and published task runs of eight frontier models.
Added
Rakazo
Self-hosted personal AI agent and persistent teammate for web, desktop, iPhone and Android, with your own choice of model and computer sandbox.
Added
Skill Recorder
Microsoft desktop app that records you doing a task once and turns the recording into a reusable skill or automation for Copilot agents.
Added
OpenAdapt
Execution layer for computer-use agents that turns a demonstrated task into a local program that repeats the clicks without model calls and stops on mismatches.
Added
Novastart
Novastart is an infinite-canvas operating system where your apps, AI agents and teammates work together on one shared whiteboard space; Free, Pro $10 and Team $20 per user.
Added
OpenWorker
Andrew Ng's open-source desktop coworker that turns requests into finished work in your files, Slack and calendar, asking before important actions.
Added
Midscene.js
Vision-driven UI automation and E2E testing framework where a GUI agent carries out natural-language steps on web, mobile and desktop apps.
Added
Hermes One
Community desktop app for installing, configuring and chatting with Hermes Agent without managing it from the terminal.
Added
RobotGo
Go library for cross-platform desktop automation and AI computer use that controls mouse, keyboard, screen, windows and processes.
Added
UFO
Microsoft's desktop agent framework that operates Windows apps and orchestrates multi-device tasks as task graphs.
Added
DeepChat
Open-source, local-first AI agent desktop client with MCP, skills, ACP support and remote control from messaging apps.
Added
5ire
Cross-platform desktop AI assistant and MCP client with a local knowledge base and support for major model providers.
Added
AstronRPA
iFlytek's open-source enterprise RPA desktop app with a low-code visual designer whose workflows can be called by AI agents.
Added
Kiln
Free desktop app and open-source library for building AI systems with evals, RAG, agents, fine-tuning and synthetic data in one workbench.
Added
nexu
Open-source desktop client that connects your OpenClaw agent to WeChat, Feishu, Slack and Discord in one click.
Added
OSWorld
Benchmark for multimodal computer-use agents on open-ended tasks in real desktop environments.
Added
Pinvou Agent
Open-source desktop AI agent workspace for work, design and coding tasks that end in finished deliverables.
Added
Agent Teams
Free desktop app where teams of AI agents take tasks from a kanban board, message each other and review each other's work.
Added
JustHireMe
Local-first desktop workbench that finds job listings, ranks your fit and generates tailored application materials.
Added
ChatMCP
Cross-platform AI chat client for desktop, mobile and web that implements the Model Context Protocol.
Added
Open Cowork
Open-source desktop app for Windows and macOS that installs Claude Code, MCP tools and skills in one click with sandbox isolation.
Added
Orkas
Local-first multi-agent desktop app where a commander model coordinates specialist agents and your installed coding CLIs.
Added
Hark Pro
Proactive personal agent on web, iOS and Android that uses its own cloud computer to shop, pay bills, book travel and handle errands.
Added
AnythingLLM
Local-first desktop and server app for chatting with your documents, running agents and connecting any LLM.
Added
AionUi
Open-source desktop cowork app that gives a GUI to CLI agents like Claude Code, Codex, OpenCode and others.
Added
Cua
Open-source infrastructure for computer-use agents: sandboxes, drivers across operating systems and benchmarks.
Added
Happy Coder
Mobile and desktop app to run and control Claude Code, Codex and other agents using your own subscriptions.
Added
Paseo
Orchestrate multiple coding agents from desktop and mobile.
Added
OpenFang
Open-source agent operating system for running autonomous agents.
Added
Eigent
Open-source cowork desktop app that runs multi-agent workflows locally.
Added
LobsterAI
NetEase Youdao's desktop agent for data analysis, slides, documents and web research.
Added
TuriX CUA
Computer-use agent that operates desktop apps.
Added
BOSS Console
Small operating system for always-on agents with real tools and a chat interface.
Added
OpenPilot
Free desktop agent for any OpenAI-compatible model; edits files and runs commands in a folder with approvals.
Added
Arro
Arro, a desktop assistant that guides you through tasks on your computer and repeats them for you.
Added
ElizaOS
Open-source TypeScript agent operating system with wallet and on-chain plugins, maintained by Eliza Research.
Added
Holo4 (H Company)
Open-weight computer-use models (27B and 35B-A3B) released Oct 1.
Added
Manus
General-purpose autonomous agent that does research and tasks in a cloud computer.
Added
SpoonOS
Agent operating system for building Web3-native AI agents.
Added
GitHub repos (53)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| AnythingLLM ↗ | 67,210 | MIT | 2026-10-20 |
| UI-TARS-desktop ↗ | 39,297 | Apache License 2.0 | 2026-10-09 |
| Next AI Draw.io ↗ | 36,280 | Apache License 2.0 | 2026-10-18 |
| AionUi ↗ | 33,580 | Apache License 2.0 | 2026-10-19 |
| Cua ↗ | 29,966 | MIT | 2026-10-21 |
| Happy Coder ↗ | 24,180 | MIT | 2026-10-21 |
| Paseo ↗ | 21,143 | Apache-2.0 (third-party components under their own licences) | 2026-10-21 |
| OpenWorker ↗ | 18,561 | MIT | 2026-10-20 |
| OpenFang ↗ | 18,213 | Apache License 2.0 | 2026-05-12 |
| Eigent ↗ | 15,571 | Apache License 2.0 | 2026-10-19 |
| Midscene.js ↗ | 15,311 | MIT | 2026-10-21 |
| Hermes One ↗ | 14,427 | MIT | 2026-10-13 |
| MemOS ↗ | 11,892 | Apache License 2.0 | 2026-09-22 |
| RobotGo ↗ | 10,871 | Apache License 2.0 | 2026-10-07 |
| UFO ↗ | 10,056 | MIT | 2026-10-14 |
Top 15 of 53 by stars. Stars and licence come from each repo, checked when the listing was last verified.
Related tasks
Popular with: Automation engineers · Related searches: AI computer-use agents
Tools are matched to tasks by category, use cases and what each tool says it does. Missing one? Submit it free.