← all releases
Tongyi MAI (Alibaba)·Nov 1, 2026·v0.3.1·open source

OpenGCUA

OpenGCUA is an open-source stack for generalist computer-use agents (GCUAs) that enables models to perform tasks by combining visual GUI interaction with programmatic code execution. It provides a comprehensive framework including a cross-device SDK, a macOS real-device harness, and evaluation trajectories for multiple frontier AI models.

AI AgentsComputer UseOpen SourceAutomation
visit website github ↗
overview

OpenGCUA is an open-source stack for generalist computer-use agents (GCUAs) that enables models to perform tasks by combining visual GUI interaction with programmatic code execution. It provides a comprehensive framework including a cross-device SDK, a macOS real-device harness, and evaluation trajectories for multiple frontier AI models.

key features
  • 01Code execution for programmatic GUI control
  • 02Cross-Device SDK for computers, browsers, and mobile
  • 03macOS real-device harness for local agent execution
  • 04OSWorld-v2 integration with evaluation trajectories
  • 05Harness-to-model decision transfer
related productsbrowse all →
MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.Letta Code SDKopen sourceThe Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.OB-1open sourceOB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.