1 repo
Awesome GitHub RepositoriesDesktop Automation Agents
Software entities that interpret visual screen information to execute tasks via simulated interactions.
Distinguishing note: Focuses on the agent entity itself rather than the framework used to build it.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Desktop Automation Agents. Refine with filters or upvote what's useful.
Awesome Desktop Automation Agents GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- microsoft/OmniParser
microsoft/OmniParser
24,377View on GitHubOmniParser is a multimodal interaction engine designed to function as a desktop automation agent. It interprets visual screen information to execute complex, multi-step tasks across operating system environments by bridging visual interface perception with language models. Through a continuous cycle of observation and command execution, the system grounds high-level natural language instructions into precise, coordinate-based actions. The project distinguishes itself by utilizing vision-based parsing to interact with software interfaces without requiring access to underlying application progr
Interprets visual screen information to execute complex tasks across operating system environments through simulated user interactions.
Jupyter Notebook
