Gemini vs open-computer-use
Gemini
gemini.google.comopen-computer-use
github.comSide by side
| Figure | Gemini | open-computer-use |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | — |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| Linux | — | Yes |
| iOS | Yes | — |
| Android | Yes | — |
| API | Yes | Yes |
| Self-hosted | — | Yes |
| Plans published | 11 | 1 |
| Spec score · AI Computer Use Agents | 9.1 (#1) | 7.8 (#6) |
| Integrations | Connected Apps let Gemini work with selected apps, but availability varies by device, country, account and Gemini surface. | The project documents setup commands for Codex CLI and App, Claude Code, Gemini CLI, and opencode, and supports manual configuration for other MCP clients. |
Plans
Gemini
- FreeFree
- Google AI UltraPrice not published
- FreeFree
- Gemini API Free tierFree
- Google AI Plus$4.99 a month
- Google AI Pro$19.99 a month
- Gemini Enterprise Business$21 a month
- Gemini Enterprise Standard/Plus$30 a month
- Google AI Ultra (5x)$99.99 a month
- Google AI Ultra (20x)$199.99 a month
In their own words
open-computer-use
open-computer-use is a free, MIT-licensed local MCP server that lets AI agents inspect and operate desktop applications through accessibility interfaces. Its nine core tools cover app discovery, accessibility-tree and screenshot capture, clicking, scrolling, dragging, typing, key presses, secondary actions, and control-value changes. The project says it runs entirely on the user’s machine and uses the accessibility layer for core app actions without taking over the physical mouse and keyboard. Setup documentation covers Codex CLI and App, Claude Code, Gemini CLI, and opencode, with manual configuration for other MCP clients. A ZCode plugin installs the skill and connects an MCP server. macOS 14 or later requires Accessibility and Screen Recording permissions. Windows and Linux use a signed-in desktop session, and Linux requires AT-SPI2. Additional window-level tools are currently available on Windows, while macOS and Linux support is in progress. Password managers are refused; app launching, focus changes, and global input injection require explicit environment-variable gates. The project warns that high-privilege automation should be used only on authorized machines.