Decision Workspace
tool-arg-coerce vs guardflow vs agentvet
Side-by-side comparison of Rust crates
43
tool-arg-coerce
experimentalv0.1.0
Fix common type slips in LLM-generated tool arguments: string->int/float/bool, single-element array->scalar, null->default. Lossy and forgiving.
44
guardflow
experimentalv0.2.0
Validators and a retry-until-valid guard for LLM output, in Rust
42
agentvet
experimentalv0.1.0
Validate LLM-generated tool args before execution. Throws a structured ToolArgError with LLM-friendly retry hints when the model hallucinates wrong types or missing fields.
Core Metrics
| tool-arg-coerce | guardflow | agentvet | |
|---|---|---|---|
| Health Score | 43 | 44 | 42 |
| Total Downloads | 21 | 96 | 59 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 3 | 0 |
| Releases | 1 | 2 | 1 |
| Last Updated | 146d ago | 64d ago | 153d ago |
| Age | 4m | 2m | 5m |
Health Breakdown
tool-arg-coerce
Maintenance
6
Quality
14
Community
6
Popularity
2
Documentation
15
guardflow
Maintenance
10
Quality
14
Community
8
Popularity
2
Documentation
10
agentvet
Maintenance
6
Quality
13
Community
6
Popularity
2
Documentation
15
Technical Details
| tool-arg-coerce | guardflow | agentvet | |
|---|---|---|---|
| Version | 0.1.0 | 0.2.0 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | MIT | MIT |
| Dependencies | 1 | 9 | 4 |
| Crate Size | 8KB | 35KB | 11KB |
| Features | 0 | 3 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2024 | 2021 |
| MSRV | 1.74 | — | 1.75 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •guardflow leads with a health score of 44/100, but none of the options score above 80.