Vibeleaderboard
← Back to Vibers
Cua
Company

Cua

Index Rank102

6 Tools · 52 Intel

Cua is a Y Combinator Spring 2025 startup founded by Francesco Bonacci, previously an engineer at Xbox and Microsoft AI, that builds open-source sandboxed VM infrastructure for AI agents that control full desktop operating systems across macOS, Linux, and Windows. The project has amassed over 19,000 GitHub stars and has been adopted by research teams at Google DeepMind, Nous Research, and Snorkel AI.

Is this you? Sign in with X to claim this profile.

Tools

Cua(github.com/trycua/cua)

Framework for building, benchmarking, and deploying AI agents that operate computers.

AI AgentsFrameworks★ 30.8kMITbuilt by trycua
Trycua Launchpad(github.com/trycua/launchpad)

Bootstraps macOS sandboxes for computer-use AI agents that drive real apps in the trycua ecosystem.

AI AgentsOpen SourcePlatforms★ 504MITbuilt by trycua
Packer Plugin Lume(github.com/trycua/packer-plugin-lume)

HashiCorp Packer plugin that builds macOS VM images with Lume for agent workloads.

Developer ToolsOpen SourceCLI Tools★ 16MPL-2.0built by trycua

Agent-ready desktops on Mac, Linux, or your own cloud, with session teleport and a local Keyvault.

AI AgentsFreeAgent Runtimebuilt by @trycua
Cua Spaces(spaces.cua.ai)

Gives AI agents their own full desktops on your Mac, owned machines, or cloud, with app session teleporting

AI AgentsFreeAgent Runtimebuilt by @trycua
Cua Agent Template(github.com/trycua/agent-template)

Sample project showing how to run an agent in a cloud sandbox with the Cua Python SDK.

AI AgentsOpen SourceCoding Agents★ 9built by trycua

Intel

AI Agents
App Use(cua.ai)

Cua's App-Use feature scopes an agent's view and control to specific applications via lightweight visual filters rather than new processes, enabling multiple agents to work in parallel on different apps on the same machine.

AI Agents

Cua got official Omarchy 4.0.1 (Arch Linux + Hyprland) running unmodified in an ARM64 VM on Apple Silicon via Lume and Apple's Virtualization.framework, verifying boot, input, networking, and native ARM64 Chromium, while noting real gaps like software-only graphics.

AI Agentsbuilt by @trycua

Explains why Cua chose Docker plus KasmVNC over QEMU/KVM for its Ubuntu desktop sandboxes: faster cold starts, no hypervisor or kernel-module requirements, and identical behavior across macOS, Windows, Linux, and CI runners.

Developer Tools