Decision Workspace
mira-judge vs mira-eval vs mira-cli
Side-by-side comparison of Rust crates
48
mira-judge
experimentalv0.5.0
LLM-as-judge scorers for Mira, backed by real providers (OpenAI Chat Completions, OpenAI Responses, and Anthropic Claude).
57
mira-eval
experimentalv0.5.0
A Rust-first, code-first evaluation framework for agents and tools
51
mira-cli
experimentalv0.5.0
The `mira` host CLI: run code-defined evals across a model matrix
Core Metrics
| mira-judge | mira-eval | mira-cli | |
|---|---|---|---|
| Health Score | 48 | 57 | 51 |
| Total Downloads | 98 | 18.5K | 206 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 18 | 0 |
| Releases | 5 | 5 | 5 |
| Last Updated | 76d ago | 76d ago | 76d ago |
| Age | 3m | 3m | 3m |
Health Breakdown
mira-judge
Maintenance
15
Quality
13
Community
6
Popularity
2
Documentation
12
mira-eval
Maintenance
15
Quality
13
Community
9
Popularity
5
Documentation
15
mira-cli
Maintenance
15
Quality
12
Community
6
Popularity
3
Documentation
15
Technical Details
| mira-judge | mira-eval | mira-cli | |
|---|---|---|---|
| Version | 0.5.0 | 0.5.0 | 0.5.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT | MIT |
| Dependencies | 6 | 9 | 9 |
| Crate Size | 18KB | 132KB | 71KB |
| Features | 0 | 4 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2024 |
| MSRV | 1.85 | 1.85 | 1.85 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •mira-eval leads with a health score of 57/100, but none of the options score above 80.