Computer-use agents just got an open-source runtime. trycua/cua, at 24.7k stars on september 20,…
computer-use agents just got an open-source runtime. trycua/cua, at 24.7k stars on september 20, ships cross-os fleets that provision a linux desktop, run a command and save a screenshot, plus benchmarks for training and evaluation.
the desktop is now a target the agent community can share.
Context
The trycua/cua repository describes itself as a platform to scale computer-use with open-source drivers, cross-OS fleets and benchmarks for training, evaluation and data generation. It is MIT licensed and was created on 31 January 2025. Its README example starts an ephemeral Linux sandbox, runs a shell command and takes a screenshot, with the same API for macOS, Windows and Android, on cloud or local QEMU runtimes. Cua-Bench evaluates on OSWorld, ScreenSpot, Windows Arena and custom tasks and exports trajectories for training.
The capabilities in the note are supported by the README. The 24.7k stars on 20 September was not confirmed: the page read showed 22,122 stars, a different date, which does not refute it. The repo is not new, since it was created in January 2025, and which release added cross-OS fleets was not found. OSWorld defines tasks, while Cua packages environments and runtimes. Agent-S and OpenCUA are agent frameworks, and browser-use is browser-only automation. That the desktop is now a target the community can share is the author's opinion.
Watch next
- Release tags for the cross-OS fleet feature and independent Cua-Bench results.
Sources
- trycua/cua (GitHub)github.com
- OSWorld (GitHub)github.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 16:16 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →