microsoft/OmniParser

Screen parsing tool for turning UI screenshots into structured elements for agents and AI models

View on index · View in 3D Map

Related repos

• Turn a UI screenshot into code using AI
• Open-source agent for automating GUI tasks using screenshots as input, built by ByteDance
• Builds multimodal agents with graph-based workflows
• turn screenshots into code using AI
• Mac automation through screen capture and AI
• Cross-platform screen capture tool with OCR
• Open-source computer vision tool that generates AI code from prompts
• turn UI screenshots into HTML and CSS code
• Cross-platform screenshot tool with annotation features