Decision Workspace
evalt vs agentcarousel vs terminal-jarvis
Side-by-side comparison of Rust crates
34
evalt
experimentalv0.1.0
Portable YAML-defined eval tests for AI agent and model harnesses
49
agentcarousel
experimentalv0.8.1
Unit tests for AI agents. Run behavioral tests in CI, score with an LLM judge, and export signed evidence your auditors accept.
57
terminal-jarvis
growingv0.1.19
A data-driven harness switcher for AI coding agents
Core Metrics
| evalt | agentcarousel | terminal-jarvis | |
|---|---|---|---|
| Health Score | 34 | 49 | 57 |
| Total Downloads | 31 | 580 | 8.7K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 0 |
| Releases | 1 | 29 | 54 |
| Last Updated | 117d ago | 121d ago | 31d ago |
| Age | 3m | 5m | 1y 2m |
Health Breakdown
evalt
Maintenance
7
Quality
9
Community
6
Popularity
2
Documentation
10
agentcarousel
Maintenance
14
Quality
11
Community
6
Popularity
3
Documentation
15
terminal-jarvis
Maintenance
17
Quality
14
Community
6
Popularity
5
Documentation
15
Technical Details
| evalt | agentcarousel | terminal-jarvis | |
|---|---|---|---|
| Version | 0.1.0 | 0.8.1 | 0.1.19 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT | MIT |
| Dependencies | 26 | 34 | 1 |
| Crate Size | 288KB | 255KB | 258KB |
| Features | 0 | 3 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2021 | 2021 |
| MSRV | — | 1.95 | 1.82 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •terminal-jarvis leads with a health score of 57/100, but none of the options score above 80.