# Browse 41 harnesses

## 30-day usage· **Aug 12–Sep 10, 2026**  
Data as of September 11, 2026 · [About the data](/content/rankings/index.html)

Rank **#1** #1 of 21 CLI agents  
Tokens **50.3T**  
Requests **512.2M**

## Capabilities and verification  
Reviewed against the HarnessRouter capability catalog on August 24, 2026. Every verified row cites its public source; rule-derived rows apply HarnessRouter's published classification rules to documented behavior. A “No public evidence” badge marks a gap in the public record, not a statement that Hermes Agent lacks them.

### Configuration & support  
- **Other models** Directly verified  
- **Custom instructions** Directly verified  
- **Skills** Directly verified  
- **Custom tools** Directly verified  
- **MCP** Directly verified  
- **Sandbox & approvals** Directly verified  
- **Sessions** Directly verified  
- **Subagents** Directly verified

### Execution & agency  
- **Workspace files** Directly verified  
- **Structured actions** Directly verified

### Environment control  
- **Browser control** Directly verified  
- **Computer control** Directly verified

### Observation & capture  
- **Screen observation** Directly verified  
- **Screenshot export** Directly verified  
- **Recording export** No public evidence

### Artifact outputs  
- **Documents** Directly verified  
- **Spreadsheets** Directly verified  
- **Presentations** Directly verified  
- **Images** Directly verified  
- **Video** Rule-derived  
- **App deployment** No public evidence

Sources: hermes-agent.nousresearch.com

### Machine interfaces  
- Headless CLI · Stable  
- MCP server · Stable

## Benchmark evidence  
Hermes Agent configurations from the HarnessRouter Care Prep benchmark, published August 10, 2026. One controlled synthetic-data task; results apply to this test, not universally.

| Model                      | End-to-end latency | Cost          |
|---------------------------|--------------------|---------------|
| gpt-5.2                  | 2m 33s             | 0.47 credits  |
| gpt-5.5                  | 1m 25s             | 40.7 credits  |
| claude-sonnet-4.6        | 2m 49s             | 39.6 credits  |
| claude-opus-4.8          | 2m 42s             | 150 credits   |

Execution success and strict grounding pass rates for these configurations are published in the observed-history capture on the benchmark report.

[See the full benchmark report](/content/benchmarks/index.html)

## Run Hermes Agent through HarnessRouter  
API harness ID: `hermes`  
Use it for autonomous-agent tasks returned through the HarnessRouter product contract.

[Create an API key and run your first task](https://app.harnessrouter.ai/login?ref=harness-run-it)  
[Run a task](/content/docs/run-a-task/index.html) [Harnesses API](/content/docs/harnesses-api/index.html)