agent-device vs Stagehand
An independent, evidence-based trust comparison of agent-device 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.
Stagehand leads on trust — 87.3/100 (Grade A) vs 79.2/100 (Grade B), a 8.1-point gap. Full breakdown below.
| Signal | agent-devicecallstack/agent-device | Stagehandbrowserbase/stagehand |
|---|---|---|
| HVTrust score | 79.2 | 87.3 |
| Evidence grade | B | A |
| Coverage grade | B | A |
| Overall rank | #98 | #31 |
| Rank in Browser & Computer Use | #7 | #2 |
| GitHub stars | 4.3k | 24.1k |
| Last updated | 1d ago | today |
| Build provenance | No | Yes |
| OSSF Scorecard | 6.4 / 10 | 5.0 / 10 |
| License | MIT | MIT |
| Downloads | 139k/wk | 1.4M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 13.0 | 18.8 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 13.9 | 12.8 |
| Maintenance / 20 | 19.9 | 19.4 |
| Adoption / 20 | 15.6 | 18.7 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Declared |
| External providers | — | 3 — Anthropic, Browserbase, OpenAI |
| Requires API keys | No | Yes |
| Plugin surface | — | extensions |
| Provenance drift | Match | Match |
Open in the live compare tool →
agent-device 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 v4.3 →