Codex vs Hermes Agent
An independent, evidence-based trust comparison of Codex and Hermes Agent, two Coding Agents projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Codex leads on trust — 93.8/100 (Grade A) vs 86.4/100 (Grade A), a 7.4-point gap. Full breakdown below.
| Signal | Codexopenai/codex | Hermes Agentnousresearch/hermes-agent |
|---|---|---|
| HVTrust score | 93.8 | 86.4 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #3 | #34 |
| Rank in Coding Agents | #1 | #5 |
| GitHub stars | 106.0k | 230.8k |
| Last updated | today | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.0 / 10 | 6.7 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | 10.9M/wk | 78k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 20.0 | 17.3 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.6 | 14.2 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 20.0 | 19.4 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 1 — OpenAI | 7 — Amazon Bedrock, Anthropic, ElevenLabs, … |
| Requires API keys | No | No |
| Plugin surface | plugins | 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 v4.3 →