AI Agent Skills

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation ·…

A modern Kubernetes GUI management desktop app for macOS & Windows. Multi-cluster support, real-time monitoring, AI assistant, terminal access, and more.

XClicker - Fast GUI autoclicker for x11 linux desktops

awesome grounding: A curated list of research papers in visual grounding

Implement a production GTAO path in Three.js. Use for half-resolution horizon sampling, reversed-depth reconstruction, bent-normal encoding, full-resolution bilateral re…

:control_knobs: Compact GUI for fine-tuning parameters and monitoring value changes

Jar Analyzer - 一个 JAR 包 GUI 分析工具，内置 AI 助手协助分析，支持 JAR DIFF 分析，方法调用关系搜索，方法调用链 DFS 算法分析，模拟 JVM 的污点分析验证 DFS 结果，字符串搜索，Java Web 组件入口分析，CFG 程序分析，JVM 栈帧分析，自定义表达式搜索等

Cross-platform desktop GUI app to clean image metadata

[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

Agentic desktop GUI client for Elasticsearch, OpenSearch, DynamoDB, MongoDB & EasySearch. Natural language queries, visual management, and monitoring. Privacy-first. Ope…

Vision-grounding plugin for browser-use agents with SoM, Florence-2, Vision–DOM alignment, adaptive visual context, and objective evaluation.

An open-sourced end-to-end VLM-based GUI Agent

Modern, lightweight and multi-cluster Kubernetes GUI. Available on Windows, macOS and Linux.

U++ is a C++ cross-platform rapid application development framework focused on programmer's productivity. It includes a set of libraries (GUI, SQL, Network etc.), and in…

[ICML 2026] RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings

Local GUI client for full-access multi-model coding agents