Awesome-GUI-Agent
★ 1.2k·Updated 2025-08-17
This repository provides a curated list of papers, projects, and resources focused on multi-modal Graphical User Interface (GUI) agents. It aims to build a comprehensive overview for developing digital assistants capable of interacting with screens.
#Multimodal AI#GUI Agents#Web Automation#Mobile Automation#Research Resources#Web Browsing#Data Analysis
01
Features
01Curated collection of papers, projects, and resources.
02Focus on multi-modal GUI agents.
03Actively maintained and open for contributions.
04Categorized sections for datasets, models, surveys, and projects.
05Includes an associated tool (Awesome-Paper-Agent) for easy contribution submission.
02
Compatibility
Web Interfaces
Web
Verified via docs
Mobile GUIs
Mobile
Verified via docs
Desktop GUIs
Desktop
Verified via docs
03
Quick start
1
$ git clone https://github.com/showlab/Awesome-GUI-Agent.git
04
Use cases
↳Researchers seeking cutting-edge work and benchmarks in GUI agent development.
↳
↳Developers looking for relevant projects and resources to build or enhance GUI automation tools.
↳Contributors who want to share new papers, projects, or insights within the multi-modal GUI agent community.
05
Alternatives
index★ 2.4k
The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web
UI-TARS-desktop★ 39.4k
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
kreuzberg★ 9.4k
A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 50+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.
groundingLMM★ 969
[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.
maro★ 929
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
video-search-and-summarization★ 1.9k
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
Comments
Log in to leave a comment
No comments yet. Be the first!