Using local computer vision to perform mouse actions via keyboard
Summary
Describes a method for using local computer vision to enable mouse actions via keyboard input.
Similar Articles
Neverclick: Desktop application for performing mouse actions with your keyboard
Neverclick is an open-source desktop application that uses computer vision to let users perform mouse actions entirely with their keyboard, enhancing productivity and accessibility.
@MiguelMaestroIA: China does it again! It has open-sourced a desktop agent that sees your screen and runs 100% locally Screen/mouse/keybo…
China has open-sourced a desktop AI agent that can see the screen and control mouse/keyboard via natural language, running entirely locally without cloud dependency.
@stevibe: I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use …
Demonstration of a local computer use agent combining Qwen3.6 35B A3B and NVIDIA LocateAnything-3B models to perform tasks like switching Mac display modes via screenshots, without requiring accessibility APIs, running entirely on local hardware.
Mouseless – keyboard-driven control of macOS/Linux/Windows
Mouseless is a cross-platform tool that enables keyboard-driven control of macOS, Linux, and Windows, allowing users to operate their computer without a mouse.
what non-coding tasks have you gotten a local model to do autonomously?
The author discusses building a small VLM for desktop GUI automation to move data between apps without APIs, expressing interest in non-coding autonomous use cases for local models.