The "gui-automation" topic on GitHub groups 7 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-vision-toolkit with 830 GitHub stars. dsh-vision-toolkit — [dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
Computer control plugin for DeepSeek Harness: fresh Accessibility observations, stale-state rejection, scoped permissions, and safe input (currently supports macos)|Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.
Desktop automation for DeepSeek Harness: hands and eyes on the whole Windows machine - screen_view returns a live PNG of the screen, desktop_control drives the real mouse, keyboard and windows at the same pixel coordinates, desktop_sequence runs a whole task in one call. Any application, not browser automation.
Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.
Windows desktop control toolkit for LLM agents: UI Automation with Chromium/Electron accessibility wake-up, verified clicks, and a capture-excluded activity indicator.