# trycua/cua > Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer. - Magnitude: 3.0 out of 10 — Steady - Stars: 31,562 total · +52 stars measured 2026-11-02, 00:10–10:55 UTC, ≈ 112 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Rust · License: MIT · Created: 2025-01-31 · Last push: 2026-11-02 - GitHub: https://github.com/trycua/cua · Homepage: https://cua.ai · Page: https://gitnova.dev/en/r/trycua/cua ## Useful for - Provision an isolated Linux desktop in the cloud and run a command in it - Connect an agent to Calculator via MCP and verify the computed result - Create a macOS VM on Apple Silicon with Lume and connect over SSH ## Why it’s here - Star-counter measurements on 2026-11-02 (UTC), 00:10–10:55: 31510 → 31562 stars (+52). This is the change over that interval. - Estimated end-of-day forecast: about +112 stars, using observed gains and the previous day. - About 8 forks a day — people are taking the code. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 2,334 - Issues and pull requests: 6,194 - Watchers: 100 - Average over the last week: 91 per day - Usual pace: 131 per day - Stars in the last hour (measured): 5 - Latest release: cua-spaces-v0.19.3 (2026-11-02) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-05 … 2026-11-03: 209, 234, 372, 212, 135, 98, 109, 129, 137, 115, 122, 93, 79, 123, 110, 218, 137, 116, 98, 65, 95, 80, 101, 98, 87, 66, 63, 111, 13, None ## Magnitude by day, last 14 days 10-20 3.7, 10-21 3.6, 10-22 3.4, 10-23 3.2, 10-24 3.0, 10-25 3.3, 10-26 3.5, 10-27 2.8, 10-28 3.0, 10-29 3.0, 10-30 3.1, 10-31 3.0, 11-01 2.8, 11-02 3.0 ## Hacker News - Show HN: CUA-S1 – A System One Model for Computer Use — 95 points, 10 comments: https://news.ycombinator.com/item?id=49767564 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-11-02 11:06 UTC, updated every 30 minutes.