Registry › Compare › Cua vs Stagehand

Cua vs Stagehand

Stagehand leads on trust: 88.6/100 (Grade A) against 74.2/100 (Grade B), a 14.4-point gap. Cua leads on maintenance; Stagehand leads on supply-chain integrity and provenance, and rests on broader evidence.

B Cua 74.2

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

trycua/cua · #248 overall · #11 Browser & Computer Use · coverage B (3/5)

Choose Cua if maintenance matters most.

+0.7Maintenance: last push today, against 1d ago

A Stagehand 88.6

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

browserbase/stagehand · #35 overall · #4 Browser & Computer Use · coverage A (4/5)

Choose Stagehand if supply-chain integrity and provenance matter most.

+8.6Safety / Integrity: 100% of recent commits signed, against 85%
+7.2Identity / Provenance: package provenance attested, against none
+3.6Adoption: 2.0M weekly downloads against 3.8k
A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

10.2

Safety / IntegrityStagehand +8.6

18.8

10.8

Identity / ProvenanceStagehand +7.2

18.0

12.6

TransparencyStagehand +0.2

12.8

20.0

MaintenanceCua +0.7

19.3

15.4

AdoptionStagehand +3.6

19.0

+5.2

Runtime calibrationCua +4.5

+0.7

Full evidence table

An independent, evidence-based trust comparison of Cua and Stagehand, two Browser & Computer Use projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	Cuatrycua/cua	Stagehandbrowserbase/stagehand
HVTrust score	74.2	88.6
Evidence grade	B	A
Coverage grade	B	A
Overall rank	#248	#35
Rank in Browser & Computer Use	#11	#4
GitHub stars	27.9k	25.5k
Last updated	today	1d ago
Build provenance	No	Yes
OSSF Scorecard	4.8 / 10	5.0 / 10
License	MIT	MIT
Downloads	4k/wk	2.0M/wk
Trust dimensions (points earned)
Safety / integrity / 25	10.2	18.8
Identity & provenance / 18	10.8	18.0
Transparency / 17	12.6	12.8
Maintenance / 20	20.0	19.3
Adoption / 20	15.4	19.0
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	2 — Anthropic, OpenAI	3 — Anthropic, Browserbase, OpenAI
Requires API keys	No	Yes
Plugin surface	plugins	extensions
Provenance drift	Match	Match

Open in the live compare tool → Cua profile Stagehand profile More Browser & Computer Use →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →