open-computer-use vs Pan-Agent
open-computer-use
github.comPan-Agent
github.comSide by side
| Figure | open-computer-use | Pan-Agent |
|---|---|---|
| Price from | Free | — |
| Free plan | Yes | — |
| Free trial | — | — |
| Open source | — | — |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| Linux | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 0 |
| Spec score · AI Computer Use Agents | 7.8 (#6) | 7.6 (#14) |
| License | The repository is distributed under the MIT license. | Pan-Agent is open source under the MIT license. |
| Platform limitation | The additional window-level tools are currently available on Windows, with macOS and Linux support in progress. | PC-control tools require X11 or XWayland on Linux; pure Wayland is unsupported. |
| Safety controls | Password managers are refused, while app launching, focus changes, and global input injection require explicit environment-variable gates. | A 103-pattern approval system asks before dangerous commands and blocks catastrophic commands by default. |
Plans
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.
Pan-Agent
Pan-Agent is a free, MIT-licensed, open-source AI assistant that runs on the user’s own machine. It can take screenshots, interpret screens, type, click, manage windows, run commands, and browse the web. The project lists more than 20 built-in tools, including terminal, filesystem, browser, web search, keyboard, mouse, vision, memory, and cron. It connects to OpenAI-compatible providers such as OpenAI, Anthropic, OpenRouter, Groq, Ollama, LM Studio, vLLM, and llama.cpp. Cron expressions can schedule agent runs, while separate profiles isolate API keys, model settings, persona, memory, and skills. Telegram, Discord, and Slack bots work without a public URL. A headless local HTTP API runs on localhost:8642 and has a documented set of 50 endpoints. Its 103-pattern approval system classifies commands and blocks catastrophic actions by default. Sessions use SQLite, and updates verify Ed25519 signatures. The project says it has no telemetry. Important limits include an unauthenticated API, Linux control requiring X11 or XWayland, unsigned Windows installers, and a macOS app that is not notarized.