Reading the repo
Opening the box…
Reading the repo
Opening the box…
Assembly instructions
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Saved setup from 4 h ago
Will it work on macOS?
Also: Docs ↗
curl -LO "https://github.com/trycua/cua/releases/download/lume-v0.7.2/lume-0.7.2-darwin-arm64.pkg.tar.gz" tar -xzf "lume-0.7.2-darwin-arm64.pkg.tar.gz"
curl -LO "https://github.com/trycua/cua/releases/download/lume-v0.7.2/lume-0.7.2-darwin-arm64.tar.gz" tar -xzf "lume-0.7.2-darwin-arm64.tar.gz"
curl -LO "https://github.com/trycua/cua/releases/download/lume-v0.7.2/lume-darwin.pkg.tar.gz" tar -xzf "lume-darwin.pkg.tar.gz"
curl -LO "https://github.com/trycua/cua/releases/download/lume-v0.7.2/lume-darwin.tar.gz" tar -xzf "lume-darwin.tar.gz"
curl -fsSL https://cua.ai/install.sh | sh
uv tool install 'cua-bench[browser]'
pip install cua
From the README, exactly as the maintainers wrote it.
No reports for macOS yet.
GitManual AI Agent reads the 11 key files and writes a step-by-step guide for macOS. Once written, it's saved for everyone.