Decision Workspace
agentforge-scorer vs prompt-eval-rubric vs agentforge-core
Side-by-side comparison of Rust crates
39
agentforge-scorer
experimentalv0.1.10
Trace analyzer and scorer (F-04): deterministic assertions, LLM-as-judge, failure clustering
42
prompt-eval-rubric
experimentalv0.1.0
Score LLM outputs against named 0.0-1.0 rubrics. Rubrics rank; validators reject. Weighted aggregation, exception-isolated scoring.
42
agentforge-core
experimentalv0.1.10
Shared types, data models, and error types for AgentForge
Core Metrics
| agentforge-scorer | prompt-eval-rubric | agentforge-core | |
|---|---|---|---|
| Health Score | 39 | 42 | 42 |
| Total Downloads | 304 | 22 | 622 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 6 | 0 | 15 |
| Releases | 1 | 1 | 1 |
| Last Updated | 134d ago | 138d ago | 135d ago |
| Age | 4m | 4m | 4m |
Health Breakdown
agentforge-scorer
Maintenance
7
Quality
11
Community
8
Popularity
3
Documentation
10
prompt-eval-rubric
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
15
agentforge-core
Maintenance
7
Quality
13
Community
9
Popularity
3
Documentation
10
Technical Details
| agentforge-scorer | prompt-eval-rubric | agentforge-core | |
|---|---|---|---|
| Version | 0.1.10 | 0.1.0 | 0.1.10 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT OR Apache-2.0 | MIT |
| Dependencies | 18 | 2 | 5 |
| Crate Size | 35KB | 10KB | 21KB |
| Features | 0 | 0 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | — | 1.74 | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •prompt-eval-rubric leads with a health score of 42/100, but none of the options score above 80.
- •agentforge-core has the most downloads (622), suggesting wider adoption.