CodeWhale vs Hermes Agent
Both are Grade A and 3.8 points apart, so choose on what you weigh most. CodeWhale leads on supply-chain integrity; Hermes Agent leads on adoption and transparency.
Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
Choose CodeWhale if supply-chain integrity matters most.
- +2.6Safety / Integrity: 68% of recent commits signed, against 2%
The agent that grows with you
Choose Hermes Agent if adoption and transparency matter most.
- +3.2Adoption: 34.5k weekly downloads against 3.6k
- +0.5Transparency: OSSF Scorecard 6.2 against 5.6
Where they differ
2 dimensions identical: Identity 18.0 · Maintenance 20.0 · Full evidence table
An independent, evidence-based trust comparison of CodeWhale 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 | CodeWhaleHmbown/CodeWhale | Hermes Agentnousresearch/hermes-agent |
|---|---|---|
| HVTrust score | 87.7 | 83.9 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #44 | #97 |
| Rank in Coding Agents | #6 | #8 |
| GitHub stars | 41.0k | 248.7k |
| Last updated | today | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 5.6 / 10 | 6.2 / 10 |
| License | MIT | MIT |
| Downloads | 4k/wk | 35k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 17.9 | 15.3 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.3 | 13.8 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 15.8 | 19.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | Implemented |
| External providers | — | 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 →