Score7.8
Popularity82.0
Riskmedium
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum8.0
Maturity7.5
Open-source/build8.4
Evidence7.2
Workflow potential8.2
Setup ease4.2
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for researchers and agent builders working on browser/computer control: review the benchmarks and model artifacts, but keep experiments sandboxed because computer-use agents can act on real pages, files, and accounts.
Who should use it
Who should skip it
Skip or sandbox it if you cannot review permissions, data access, and failure modes before use.
Risk explanation
computer-use agents can operate real accounts or files if not sandboxed; model and dataset terms may differ from the repo license.