Registry › Compare › agent-device vs OpenClaw

agent-device vs OpenClaw

Both are Grade A and 1.7 points apart, so choose on what you weigh most. agent-device leads on supply-chain integrity and transparency; OpenClaw leads on adoption and rests on broader evidence. Note: agent-device's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.

A agent-device 91.7

Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.

callstack/agent-device · #13 overall · #1 Browser & Computer Use · coverage B (3/5)

Choose agent-device if supply-chain integrity and transparency matter most.

+1.1Safety / Integrity: 97% of recent commits signed, against 96%
+0.7Transparency: OSSF Scorecard 6.5 against 5.7

A OpenClaw 90.0

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

openclaw/openclaw · #25 overall · #4 Browser & Computer Use · coverage A (4/5)

Choose OpenClaw if adoption matters most.

+3.8Adoption: 4.0M weekly downloads against 291k
A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

20.5

Safety / Integrityagent-device +1.1

19.4

14.0

Transparencyagent-device +0.7

13.3

19.9

MaintenanceOpenClaw +0.1

20.0

16.2

AdoptionOpenClaw +3.8

20.0

+3.1

Runtime calibrationagent-device +3.8

-0.7

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of agent-device and OpenClaw, 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	agent-devicecallstack/agent-device	OpenClawopenclaw/openclaw
HVTrust score	91.7	90.0
Evidence grade	A	A
Coverage grade	B	A
Overall rank	#13	#25
Rank in Browser & Computer Use	#1	#4
GitHub stars	5.0k	392.0k
Last updated	1d ago	today
Build provenance	Yes	Yes
OSSF Scorecard	6.5 / 10	5.7 / 10
License	MIT	MIT
Downloads	291k/wk	4.0M/wk
Trust dimensions (points earned)
Safety / integrity / 25	20.5	19.4
Identity & provenance / 18	18.0	18.0
Transparency / 17	14.0	13.3
Maintenance / 20	19.9	20.0
Adoption / 20	16.2	20.0
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	—	5 — Anthropic, Google Gemini, Mistral AI, …
Requires API keys	No	No
Plugin surface	plugins	extensions
Provenance drift	Match	Match

Open in the live compare tool → agent-device profile OpenClaw 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 →