Cua
Open-source computer-use platform: full desktops for agents (Cua Spaces), a desktop-automation driver with MCP, local macOS/Linux VMs (Lume) and Cua Bench.
Tags
Description
Cua Spaces gives agents macOS VMs built locally on a Mac or Linux images, on your own machines or cloud account, with shared human/agent cursors and "teleport" of signed-in apps. Cua Driver lets agents inspect and operate native apps and browsers on macOS, Windows and Linux via CLI, MCP or typed SDKs. Also includes Lume (local VMs), the cua SDK/CLI for sandboxes, CUA-S1 small models for computer-use decisions and Cua Bench for tasks and evaluation. Licensing: MIT for the SDK, CLI, Driver, Lume and most of the repo; Cua Spaces and Cua Driver Bench are source-available under FSL-1.1-MIT. Spaces is free (up to 2 live sessions and 20 remote hours a month), Pro is $18/month and Teams $30/seat/month.
Agent access
Related
- E2B Desktop Sandbox: Open-source, isolated virtual Linux desktops for computer-use agents, built on E2B sandboxes, with Python and JavaScript SDKs and desktop streaming.
- OSWorld: NeurIPS 2024 benchmark of multimodal agents on open-ended tasks in real computer environments.
- microsandbox: Easy, fast, programmable, local-first microVM runtime for untrusted workloads.
- Anchor Browser: Cloud browser infrastructure for computer-use and browser agents; agents can obtain an API key programmatically.
Guides & comparisons
- Self-hosted sandboxes for agents compared (Comparison): Six ways to isolate agent-run code on hardware you control (OpenSandbox, AIO Sandbox, microsandbox, Kubernetes Agent Sandbox, Anthropic's sandbox-runtime and Docker Sandboxes' local mode) compared on isolation, where they run, agent interface, network and secret controls, maturity and license.
- Agent benchmarks compared (Comparison): Ten widely cited agent benchmarks (SWE-bench, Terminal-Bench, tau-bench, BFCL, MCPMark, GAIA, BrowseComp, WebArena, Mind2Web and OSWorld) compared on what they measure, how many tasks they have, where the agent runs, how runs are scored, where results are published and how they are licensed.
Sources
- https://github.com/trycua/cua
- https://cua.ai/pricing
- https://cua.ai/docs/llms.txt
- https://pypi.org/project/cua-agent/
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)