https://github.com/microsoft/OmniParser
A simple screen parsing tool towards pure vision based GUI agent
https://github.com/microsoft/OmniParser
Last synced: over 1 year ago
JSON representation
A simple screen parsing tool towards pure vision based GUI agent
- Host: GitHub
- URL: https://github.com/microsoft/OmniParser
- Owner: microsoft
- License: cc-by-4.0
- Created: 2024-09-20T05:18:18.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2025-03-17T20:18:19.000Z (over 1 year ago)
- Last Synced: 2025-03-23T07:01:09.208Z (over 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 42.2 MB
- Stars: 20,939
- Watchers: 170
- Forks: 1,710
- Open Issues: 174
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Security: SECURITY.md
Awesome Lists containing this project
- Awesome-GitHub-Repo - OmniParser - 微软开源的屏幕内容解析工具,能够将任意UI截图转换为结构化数据,识别按钮、图标、文本等元素及其位置,为GUI自动化提供基础能力。 (AI开源项目 / AI Agent)
- awesomeLibrary - OmniParser - A simple screen parsing tool towards pure vision based GUI agent (语言资源库 / python)
- awesome-llm-services - OmniParser
- awesome-github-projects - OmniParser - A simple screen parsing tool towards pure vision based GUI agent ⭐25,010 `Jupyter Notebook` ⚡ (🌐 Web Development - Frontend)
- acu - Code
- awesome-ui-agents - code
- awesome-mac-mini-homeserver - OmniParser - Screen parsing for GUI agents.   (Agentic AI  / Browser and computer-use agents)
- AiTreasureBox - microsoft/OmniParser - 11-03_23785_-1](https://img.shields.io/github/stars/microsoft/OmniParser.svg)|A simple screen parsing tool towards pure vision based GUI agent| (Repos)
- awesome-local-llm - OmniParser - a simple screen parsing tool towards pure vision based GUI agent (Tools / Computer Use)
- awesome-computer-use - OmniParser - Screen parsing for pure vision-based GUI agents. `5k ⭐`. (Vision and Grounding Models)
- Awesome-GUI-Agents - Github
- awesome-azure-openai-copilot - OmniParser - Vision-based GUI parsing for screen-grounded agent control. (Agent Frameworks)
- awesome-llm-tools - OmniParser - based GUI agent screen parsing tool | Python / Model | (1. Local Agents / Computer Use & OS Agents)
- awesome-opensource-ai - OmniParser - Vision-based GUI parsing model and tooling for computer-use agents.  (2. Model Codebases & Model Families)
- awesome-side-quests - microsoft/OmniParser - based GUI agents — identifies UI elements from screenshots for AI agents (Stale / Data Science & Visualization)
- awesome-vision-ai-stack - OmniParser - Screen parsing for GUI grounding and action planning. (UI Understanding and Computer Use / Projects and references)
- awesome-ai-tools - Microsoft OmniParser v2 - brightgreen) — Not an agent — pure-vision GUI-grounding module that 'tokenizes' screenshots. Paired with OmniTool (dockerized Win11 VM). · `OSS` · Python · ≈24.9k★ *GitHub API, 2026-06-19* (🖱️ Computer-Use & Browser Agents / Builder / API layer)
- awesome - microsoft/OmniParser - A simple screen parsing tool towards pure vision based GUI agent (Jupyter Notebook)