Decision Workspace
microloop vs agentic-eval vs iron_types
Side-by-side comparison of Rust crates
42
microloop
experimentalv0.2.0
Ultra-fast runtime safety layer for autonomous agents — detects agent tool call loops before they burn API credits
58
agentic-eval
experimentalv0.14.4
Evaluate programs, CLI commands, programming languages, AI frameworks, and VM/sandbox systems for agentic AI use across four axes — token efficiency, determinism, reliability, and safety — under popular tokenizers (OpenAI GPT-4/GPT-4o, Anthropic Claude). Includes a CLI effect classifier, curated language/framework/VM profiles, and a self-describing ontology.
49
iron_types
experimentalv0.3.0
Shared types and data structures for Iron Cage AI agent management
Core Metrics
| microloop | agentic-eval | iron_types | |
|---|---|---|---|
| Health Score | 42 | 58 | 49 |
| Total Downloads | 298 | 130 | 1.3K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 3 | 32 | 20 |
| Releases | 1 | 3 | 2 |
| Last Updated | 100d ago | 72d ago | 297d ago |
| Age | 3m | 3m | 10m |
Health Breakdown
microloop
Maintenance
8
Quality
13
Community
8
Popularity
3
Documentation
10
agentic-eval
Maintenance
15
Quality
15
Community
10
Popularity
3
Documentation
15
iron_types
Maintenance
7
Quality
16
Community
10
Popularity
4
Documentation
12
Technical Details
| microloop | agentic-eval | iron_types | |
|---|---|---|---|
| Version | 0.2.0 | 0.14.4 | 0.3.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | AGPL-3.0-or-later | MIT |
| Dependencies | 5 | 2 | 6 |
| Crate Size | 18KB | 121KB | 20KB |
| Features | 0 | 3 | 5 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2021 | 2021 |
| MSRV | — | 1.75 | 1.70 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •agentic-eval leads with a health score of 58/100, but none of the options score above 80.
- •iron_types has the most downloads (1.3K), suggesting wider adoption.