Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops.
30
Public repositories
20,163
Total stars
367
Followers
The GitHub presence of trycua showcases a wide range of repositories focused on open-source infrastructure for Computer-Use Agents. Notable projects include cua, a comprehensive framework for training AI agents, and pylume, a library for managing virtual machines. The organization primarily utilizes Python, TypeScript, and JavaScript in its development efforts.
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.
No description provided for this repository.
A lightweight Python library to create, run and manage macOS and Linux virtual machines (VMs) natively on Apple Silicon.
Packer plugin for Lume
A sample use of Cua Python SDK for running an agent on a cloud sandbox
Learn how to use CUA (our Computer Using Agent) via the API on multiple computer environments.
VNC client web application
No description provided for this repository.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Windows inside a Docker container.
No description provided for this repository.
The agent that grows with you
This demo shows a multi-turn conversation with an AI agent running inside a Temporal workflow.
Node.js library for creating Guacamole-compatible servers. Guacamole is a RDP/VNC/SSH/Telnet client for HTML5 browsers.
QEMU in a Docker container.
A Python package that makes it easy for developers to create AI apps powered by various AI providers.
Test config for comin system-manager deployment on non-NixOS Linux
Powerful system container and virtual machine manager
Electron companion to desktop-test-app — loads arbitrary URLs for cua-sandbox MITM proxy integration tests
Desktop input event logger for cua-sandbox integration tests
Manage system config using nix on any distro
GitOps For NixOS Machines
A gateway for seamless access to your RDP-Sessions in any HTML5-compliant browser
Convert PWA manifest URLs to native-looking Android APKs using WebView (no Chrome TWA banners)
Todo-list PWA gym for agent evaluation — installable as Android TWA
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
TouchTest APK for CUA Android multi-touch integration tests
Web client prototype for scrcpy.
Procedural color gradients using Perlin noise mapped through harmonic music interval ratios
Trycua builds open-source tools and infrastructure for Computer-Use Agents. Their repositories include frameworks, libraries, and resources that facilitate the training and evaluation of AI agents across different operating systems.
Trycua primarily uses Python, TypeScript, and JavaScript in its GitHub projects. These languages support the development of various tools, including sandboxes and SDKs for AI agents.
Yes, trycua's repositories are public on GitHub. This openness allows developers and researchers to access and contribute to their projects focused on AI agents and related technologies.
Monitor Cua with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account