agent-device vs Skyvern
agent-device leads on trust: 91.8/100 (Grade A) against 86.2/100 (Grade A), a 5.6-point gap. agent-device leads on adoption; Skyvern leads on supply-chain integrity 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.
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.
Choose agent-device if adoption matters most.
- +1.5Adoption: 291k weekly downloads against 1.5k
Automate browser based workflows with AI
Choose Skyvern if supply-chain integrity matters most.
- +0.7Safety / Integrity: 100% of recent commits signed, against 97%
- A vs BEvidence coverage: 4 of 5 independent signal types, against 3
Where they differ
2 dimensions identical: Identity 18.0 · Maintenance 20.0 · Full evidence table
An independent, evidence-based trust comparison of agent-device and Skyvern, 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 | SkyvernSkyvern-AI/skyvern |
|---|---|---|
| HVTrust score | 91.8 | 86.2 |
| Evidence grade | A | A |
| Coverage grade | B | A |
| Overall rank | #12 | #77 |
| Rank in Browser & Computer Use | #1 | #8 |
| GitHub stars | 5.0k | 23.2k |
| Last updated | today | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.5 / 10 | 7.0 / 10 |
| License | MIT | AGPL-3.0 |
| Downloads | 291k/wk | 2k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 20.5 | 21.2 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 14.0 | 14.4 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 16.2 | 14.7 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | — | 5 — Anthropic, Google Gemini, Multi-provider (LiteLLM), … |
| Requires API keys | No | Yes |
| Plugin surface | plugins | — |
| Provenance drift | Match | Unknown |
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 →