Decision Workspace
llm-guard-ml vs wardline-core vs wardline-guards
Side-by-side comparison of Rust crates
40
llm-guard-ml
experimentalv0.1.0
ONNX-runtime-backed scanners for llm-guard. Catches paraphrased / novel prompt-injection attacks the rules tier can't. CPU by default; CUDA / CoreML / DirectML opt-in.
52
wardline-core
experimentalv0.1.0
Synchronous, embeddable guardrail evaluation core: the Guard trait, Verdict, fail policies, and the blocking pipeline executor.
49
wardline-guards
experimentalv0.1.0
Built-in reference Guard implementations for Wardline (regex, rate limit, PII, LLM heuristics).
Core Metrics
| llm-guard-ml | wardline-core | wardline-guards | |
|---|---|---|---|
| Health Score | 40 | 52 | 49 |
| Total Downloads | 23 | 39 | 20 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 3 | 1 |
| Releases | 1 | 1 | 1 |
| Last Updated | 145d ago | 25d ago | 25d ago |
| Age | 4m | 25d | 25d |
Health Breakdown
llm-guard-ml
Maintenance
6
Quality
15
Community
5
Popularity
2
Documentation
12
wardline-core
Maintenance
11
Quality
16
Community
8
Popularity
2
Documentation
15
wardline-guards
Maintenance
11
Quality
14
Community
7
Popularity
2
Documentation
15
Technical Details
| llm-guard-ml | wardline-core | wardline-guards | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.0 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | MIT OR Apache-2.0 | MIT OR Apache-2.0 |
| Dependencies | 5 | 3 | 2 |
| Crate Size | 23KB | 41KB | 14KB |
| Features | 4 | 2 | 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
- •wardline-core leads with a health score of 52/100, but none of the options score above 80.