20 UI-TARS Desktop alternatives
UI-TARS Desktop: ByteDance's open-source desktop app that lets the UI-TARS vision-language model operate your computer and browser with mouse and keyboard. 20 apps do similar work, most sharing macOS, Browser Automation and Desktop App, ranked by how much they have in common with UI-TARS Desktop.
-
pungme
An open-source Mac app that gives Claude Code a real browser, a live iOS Simulator and its own git worktree per chat.
Also: Browser Automation, Desktop App, macOS, Open Source
-
The open-source library that lets AI agents actually use websites — clicking, typing, and reading like a person.
-
Cua AI, Inc.
Open-source computer-use infrastructure: a desktop driver, cloud desktop fleets, local macOS VMs and a benchmark for agents that click.
Also: Computer Use, macOS, Open Source
-
Felafax, Inc.
Free, open-source desktop browser that coding agents such as Claude Code, Codex and Cursor drive using your real logged-in accounts.
Also: Browser Automation, Desktop App, Open Source
-
Manus AI
A general autonomous AI agent that executes multi-step tasks end to end in its own cloud environment.
Also: Browser Automation, Computer Use
-
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.
Also: Browser Automation, Computer Use
-
Opera
Opera's agentic AI browser: Neon Chat, a Neon Do agent that acts on web pages, deep research, and MCP/CLI hooks for your own agents.
Also: Browser Automation, Computer Use
-
Wispr
Voice dictation that works in every app and cleans up as you speak — no filler words, correct formatting, right tone.
-
The Browser Company
An AI browser for the workday from The Browser Company: a chat that reads your tabs and connected tools, a Morning Brief, meeting pages and AI-made decks.
-
ABBYY
Desktop PDF editor built around ABBYY's AI-based OCR: turn scans into editable Word, Excel or searchable PDF in 198 recognition languages.
-
O-mega Enterprise Inc.
Hold a key, speak, and Yap types your words into any app. Speech recognition runs on your Mac or PC, so your audio is never uploaded.
-
Voice typing for Mac and Windows that turns speech into edited, formatted text in any app — plus screenshot questions and spoken edits behind one shortcut.
-
Anthropic
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.
Also: Computer Use, Desktop App
-
_github.com-microsoft-mxc.png)
Microsoft
Microsoft's open-source, policy-driven sandbox SDK for running agents, model-generated code, tools and plugins with only the files and network access you grant.
Also: Open Source, Windows
-
Aside Computer Inc.
AI browser that runs real tasks inside your logged-in accounts, with credentials sealed in an on-device vault the agent never reads.
Also: Browser Automation, Desktop App
-
The Plow Collective PBC
Mac app that exposes your browser, CLI, files and saved logins to Claude, Codex or any MCP agent — with an approval gate on every request.
Also: Browser Automation, macOS
-
macOS assistant that works at your cursor — rewrite selected text in place, dictate into any field, and explain whatever is on screen, without switching to a chat tab.
Also: Desktop App, macOS
-
Raycast
Raycast AI combines leading models with powerful extensions - right on your OS
Also: Desktop App, macOS
-
coconutStudio
A native macOS notes app that parks notes along your screen edge and keeps an AI agent inside them, encrypted on-device.
Also: Desktop App, macOS
-
Unsloth AI
Open-source desktop app to run, serve and fine-tune text, image, video and audio models entirely on your own machine.
Also: Desktop App, Open Source