agent-device vs Browser Use
Both are Grade A and 4.2 points apart, so choose on what you weigh most. agent-device leads on supply-chain integrity and transparency; Browser Use 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.
Open source device layer for AI coding agents: a CLI, MCP server, and typed Node.js API to control mobile, web, TV, and desktop apps on devices and simulators, locally or in the cloud.
Choose agent-device if supply-chain integrity and transparency matter most.
- +5.9Safety / Integrity: 99% of recent commits signed, against 11%
- +1.0Transparency: OSSF Scorecard 6.1 against 4.9
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Choose Browser Use if adoption matters most.
- +3.3Adoption: 2.1M weekly downloads against 682.6k
- 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 Browser Use, 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 | Browser Usebrowser-use/browser-use |
|---|---|---|
| HVTrust score | 91.6 | 87.4 |
| Evidence grade | A | A |
| Coverage grade | B | A |
| Overall rank | #16 | #68 |
| Rank in Browser & Computer Use | #1 | #8 |
| GitHub stars | 5.4k | 121.0k |
| Last updated | today | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.1 / 10 | 4.9 / 10 |
| License | MIT | MIT |
| Downloads | 683k/wk | 2.1M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 20.1 | 14.2 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.7 | 12.7 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 16.7 | 20.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | — | 3 — Anthropic, Google Gemini, OpenAI |
| Requires API keys | No | Yes |
| Plugin surface | plugins | — |
| 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 v4.4 →