Vision Use: Enabling the DeepSeek Harness Agent to See the Screen and Control the Windows Desktop
The Vision Use plugin for DeepSeek Harness (DSH) addresses the issue of agents being unable to directly perceive the desktop environment. By integrating visual channels and system-level operation interfaces, it provides features such as screen capture, mouse movement and clicking, keyboard input, and sending key combinations. It supports both native Windows and WSL2 environments and is easy to install. Once enabled, an agent can control desktop applications using natural-language instructions, such as searching the web or opening Notepad to type text. The plugin is privacy-focused: screenshots are sent only as context and do not generate network requests. Note the compatibility limitations related to Chinese input and some applications, such as Chromium and WinUI.
Read Moredsh-computer-use: General-Purpose Computer Use Capabilities of DeepSeek Harness
`dsh-computer-use` is a plugin for DeepSeek Harness that provides agents with a unified computer operation interface. It wraps the underlying drivers through `ctx.computerUse`, supports multiple backends such as Playwright and the Windows native assistant, and integrates accessibility and visual perception modes. The plugin provides security mechanisms, Cookie Bridge support, and depends on several DSH base plugins. Its configuration is flexible and can be modified in real time via the GUI, but there are platform limitations and configuration isolation issues caused by App-Bound Encryption. When using it, be careful to import only required data and configure a domain whitelist.
Read Morebeijingwahw/dsh-computer-use-plugin: DSH-based pure vision Computer Use plugin
`beijingwahw/dsh-computer-use-plugin` is a pure vision Computer Use plugin within the DeepSeek Harness (DSH) ecosystem. It abandons traditional UI tree or Accessibility API dependencies, understanding the interface through screenshots and supporting cross-platform desktop operations such as clicking, inputting, scrolling, and dragging on Windows, macOS, and Linux. The plugin's core capabilities include Set-of-Mark-based visual localization assistance, a three-stage state anchor protocol, long-task orchestration using the Planner-Actor architecture, and OCR semantic verification (supporting both Chinese and English). To ensure stability and security, it incorporates built-in behavioral verification, infinite loop prevention, budget control, and sensitive credential input blocking.
Read MoreDSH Computer Use for Windows: Windows Desktop Operation Tools for DeepSeek Harness
`Altairpaca/dsh-computer-use-windows` is a Windows desktop automation plugin for DeepSeek Harness (DSH), currently in the experimental Alpha phase. The project aims to address challenges in Windows automation, such as irrelevant windows appearing in screenshots, unstable coordinate control, and OCR text drift. Core features include window-bound screenshots, robust OCR, post-click verification, mouse and keyboard input control, window management, batch execution entry points, optional vision model integration, and local health checks. The system supports a pure OCR mode to keep screenshots local and allows configuration of OpenAI-compatible vision providers. Requirements for installation and execution are Windows 11, PowerShell 7.4+, and Node.js.
Read More