Gemini CLI vs Hermes Agent
Hermes Agent leads on trust: 83.3/100 (Grade A) against 77.2/100 (Grade B), a 6.1-point gap. Gemini CLI rests on broader evidence; Hermes Agent leads on supply-chain integrity and provenance. Note: Hermes Agent's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.
An open-source AI agent that brings the power of Gemini directly into your terminal.
Choose Gemini CLI if breadth of evidence matters most.
- A vs BEvidence coverage: 4 of 5 independent signal types, against 3
The agent that grows with you
Choose Hermes Agent if supply-chain integrity and provenance matter most.
- +7.2Identity / Provenance: package provenance attested, against none
- +3.9Safety / Integrity: OSSF Scorecard 5.8 against 4.7
- +0.9Transparency: OSSF Scorecard 5.8 against 4.7
Where they differ
1 dimension identical: Adoption 19.6 · Full evidence table
An independent, evidence-based trust comparison of Gemini CLI 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.
Full evidence
| Signal | Gemini CLIgoogle-gemini/gemini-cli | Hermes Agentnousresearch/hermes-agent |
|---|---|---|
| HVTrust score | 77.2 | 83.3 |
| Evidence grade | B | A |
| Coverage grade | A | B |
| Overall rank | #236 | #129 |
| Rank in Coding Agents | #10 | #8 |
| GitHub stars | 108.8k | 262.4k |
| Last updated | 1d ago | today |
| Build provenance | No | Yes |
| OSSF Scorecard | 4.7 / 10 | 5.8 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | 450k/wk | 85k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 10.9 | 14.8 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 12.5 | 13.4 |
| Maintenance / 20 | 19.9 | 20.0 |
| Adoption / 20 | 19.6 | 19.6 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 1 — Google Gemini | 7 — Amazon Bedrock, Anthropic, ElevenLabs, … |
| Requires API keys | Yes | No |
| Plugin surface | extensions | 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 →