agent-device vs OpenClaw
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.
OpenClaw leads on trust — 89.5/100 (Grade A) vs 79.7/100 (Grade B), a 9.8-point gap. Full breakdown below.
| Signal | agent-devicecallstack/agent-device | OpenClawopenclaw/openclaw |
|---|---|---|
| HVTrust score | 79.7 | 89.5 |
| Evidence grade | B | A |
| Coverage grade | B | A |
| Overall rank | #136 | #18 |
| Rank in Browser & Computer Use | #8 | #2 |
| GitHub stars | 4.4k | 389.2k |
| Last updated | today | today |
| Build provenance | No | Yes |
| OSSF Scorecard | 6.6 / 10 | 4.7 / 10 |
| License | MIT | NOASSERTION |
| Downloads | 129k/wk | 3.3M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 13.2 | 18.4 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 14.1 | 12.5 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 15.6 | 20.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | — | 4 — Anthropic, Google Gemini, Mistral AI, … |
| Requires API keys | No | No |
| Plugin surface | — | extensions |
| Provenance drift | Match | Match |
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 v4.3 →