Decision Workspace
llm-guard vs hanzo-guard vs parry-guard-ml
Side-by-side comparison of Rust crates
44
llm-guard
experimentalv0.2.0
Zero-copy guardrails for LLM input/output. Pure-Rust scanners (prompt-injection, role-override, secret leakage, PII, invisible text, deobfuscation, token limit).
53
hanzo-guard
experimentalv0.1.4
LLM I/O sanitization and safety layer - the 'condom' for AI
48
parry-guard-ml
experimentalv0.1.5
ML-based injection detection (DeBERTa v3)
Core Metrics
| llm-guard | hanzo-guard | parry-guard-ml | |
|---|---|---|---|
| Health Score | 44 | 53 | 48 |
| Total Downloads | 50 | 1.1K | 326 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 1 | 1 | 13 |
| Releases | 3 | 5 | 7 |
| Last Updated | 8d ago | 13d ago | 24d ago |
| Age | 13d | 4m | 2m |
Health Breakdown
llm-guard
Maintenance
13
Quality
14
Community
6
Popularity
2
Documentation
9
hanzo-guard
Maintenance
17
Quality
15
Community
7
Popularity
4
Documentation
10
parry-guard-ml
Maintenance
11
Quality
15
Community
9
Popularity
3
Documentation
10
Technical Details
| llm-guard | hanzo-guard | parry-guard-ml | |
|---|---|---|---|
| Version | 0.2.0 | 0.1.4 | 0.1.5 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | MIT | MIT |
| Dependencies | 4 | 12 | 12 |
| Crate Size | 61KB | 31KB | 32KB |
| Features | 1 | 7 | 5 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2021 | 2021 |
| MSRV | 1.85 | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •hanzo-guard leads with a health score of 53/100, but none of the options score above 80.