An independent, evidence-based trust comparison of Deep Agents and Vercel AI SDK, two Agent Frameworks projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
| Signal | Deep Agentslangchain-ai/deepagents | Vercel AI SDKvercel/ai |
|---|---|---|
| HVTrust score | 100.0 | 100.0 |
| Evidence grade | A | A |
| Overall rank | #10 | #9 |
| Rank in Agent Frameworks | #2 | #1 |
| GitHub stars | 25.7k | 25.4k |
| Last updated | today | today |
| Build provenance | No | Yes |
| OSSF Scorecard | 6.0 / 10 | 7.5 / 10 |
| License | MIT | NOASSERTION |
| Downloads | 1.4M/wk | 15.3M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 12.5 | 21.9 |
| Identity & provenance / 20 | 10.8 | 18.0 |
| Transparency / 17 | 13.6 | 14.9 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 18.8 | 20.0 |
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 v4.0 →