EvoCUA: Evolving Computer Use Agent

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

R-HORIZON: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?

Fully Open Framework for Democratized Multimodal Training

R-HORIZON: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

ScaleCUA is the open-sourced computer use agents that can operate on cross-platform environments (Windows, macOS, Ubuntu, Android).

This is the official code base of AgentNetTool in OpenCUA. Website: https://opencua.xlang.ai/

OpenCUA: Open Foundations for Computer-Use Agents

[ACL 2025] Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Community maintained hardware plugin for vLLM on Ascend

A curated collection of resources, tools, and frameworks for developing GUI Agents.

UI-Venus is a native UI agent designed to perform precise GUI element grounding and effective navigation using only screenshots as input.

Solve Visual Understanding with Reinforced VLMs

[AAAI 2026] GUI-G²: Gaussian Reward Modeling for GUI Grounding

Enable AI to control your PC. This repo includes the WorldGUI Benchmark and GUI-Thinker Agent Framework.

Think Beyond Images

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Renderer for the harmony response format to be used with gpt-oss

Unleashing the Power of Reinforcement Learning for Math and Code Reasoners

Scaling RL on advanced reasoning models

RM-R1: Unleashing the Reasoning Potential of Reward Models

Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent