{"id":"openai-computer-use","name":"OpenAI computer use","maker":"OpenAI","url":"https://developers.openai.com/api/docs/guides/tools-computer-use","repo":"openai/openai-cua-sample-app","summary":"A tool in the OpenAI API that lets a model propose clicks, typing and scrolling from screenshots to operate a browser or desktop.","details":"The developer runs the environment and carries out each proposed action, then sends back the next screenshot. A sample application shows a loop with several browser back ends. It requires an OpenAI API key.","open_source":false,"hosted":true,"speaks":["openai-api"],"verified":"2026-11-15","category":"browser","category_name":"Browser automation and computer use","page":"https://modelmoot.com/tools/openai-computer-use","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}