Hermes Agent vs Qwen Code
An independent, evidence-based trust comparison of Hermes Agent and Qwen Code, two Coding Agents projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Qwen Code leads on trust — 90.8/100 (Grade A) vs 81.1/100 (Grade A), a 9.7-point gap. Full breakdown below.
| Signal | Hermes Agentnousresearch/hermes-agent | Qwen CodeQwenLM/qwen-code |
|---|---|---|
| HVTrust score | 81.1 | 90.8 |
| Evidence grade | A | A |
| Coverage grade | B | A |
| Overall rank | #57 | #6 |
| Rank in Coding Agents | #8 | #2 |
| GitHub stars | 225.4k | 26.7k |
| Last updated | today | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.5 / 10 | 6.4 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | 78k/wk | 93k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 17.0 | 20.5 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 14.0 | 13.9 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 19.4 | 17.2 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 5 — Amazon Bedrock, Anthropic, Firecrawl, … | 3 — Anthropic, Google Gemini, OpenAI |
| Requires API keys | No | No |
| Plugin surface | plugins | plugins |
| Provenance drift | Warning | 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 v4.2 →