Decision Workspace
agent-reflection vs eval-core vs mira-eval
Side-by-side comparison of Rust crates
41
agent-reflection
experimentalv0.1.0
Self-evaluation and reflection loop for LLM agent outputs
54
eval-core
experimentalv0.4.0
A testing framework for LLM agents: prompt-based test cases with built-in assertions on tool calls, parameters, and text/math output — bring your own harness.
54
mira-eval
experimentalv0.4.0
A Rust-first, code-first evaluation framework for agents and tools
Core Metrics
| agent-reflection | eval-core | mira-eval | |
|---|---|---|---|
| Health Score | 41 | 54 | 54 |
| Total Downloads | 15 | 130 | 845 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 13 |
| Releases | 1 | 4 | 4 |
| Last Updated | 49d ago | 22d ago | 2d ago |
| Age | 1m | 24d | 21d |
Health Breakdown
agent-reflection
Maintenance
10
Quality
15
Community
5
Popularity
1
Documentation
10
eval-core
Maintenance
18
Quality
12
Community
6
Popularity
3
Documentation
15
mira-eval
Maintenance
14
Quality
13
Community
9
Popularity
3
Documentation
15
Technical Details
| agent-reflection | eval-core | mira-eval | |
|---|---|---|---|
| Version | 0.1.0 | 0.4.0 | 0.4.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT OR Apache-2.0 | MIT |
| Dependencies | 0 | 11 | 9 |
| Crate Size | 2KB | 81KB | 130KB |
| Features | 0 | 0 | 4 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2024 | 2024 |
| MSRV | — | 1.88 | 1.85 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •eval-core leads with a health score of 54/100, but none of the options score above 80.
- •mira-eval has the most downloads (845), suggesting wider adoption.