OmniParser

by microsoft · Developer Tools

A simple screen parsing tool towards pure vision based GUI agent

New0 ratings25,374 starsActive
Developer ToolsDeveloper ToolJupyter NotebookPython
↓ Download v.2.0.1GitHub⚑ Report
OmniParser — image 1

About this project

OmniParser: Screen Parsing tool for Pure Vision Based GUI Agent 📢 [Project Page] [V2 Blog Post] [Models V2] [Models V1.5] [HuggingFace Space Demo] OmniParser is a comprehensive method for parsing user interface screenshots into structured and easy-to-understand elements, which significantly enhances the ability of GPT-4V to generate actions that can be accurately grounded in the corresponding regions of the interface. News — [2026/7] We add a YOLOv9-E interactive region detector. Its inference-only weight is available in Hugging Face PR #37. — [2025/3] We support local logging of trajecotry so that you can use OmniParser+OmniTool to build training data pipeline for your…

Technologies

ShellPythonPowerShellDockerfileJupyter Notebook

Project health

Recently updated
Last updatelast month
Contributors10
Latest releasev.2.0.1
Open issues & PRs230
LicenseCC-BY-4.0
On GitHubsince 2024

GitHub

25,374
stars
2,231
forks
10
contributors
230
open issues & PRs
Jupyter Notebook
language
last month
last commit
View on GitHub ↗All releases ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review OmniParser.

Built by

microsoft
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain microsoft/OmniParser? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like