Decision Workspace
tool-loop-guard vs rskit-agent vs tool-arg-defaults
Side-by-side comparison of Rust crates
42
tool-loop-guard
experimentalv0.1.0
Detect when an LLM agent gets stuck calling the same tool with the same args. Sliding-window guard that raises on repeated (tool_name, args) pairs. Custom key function support, zero heavy deps.
56
rskit-agent
experimentalv0.2.0-alpha.5
Agentic loop — Provider + Tools + Hooks in a turn-based execution engine
42
tool-arg-defaults
experimentalv0.1.0
Apply per-tool default kwargs to LLM-generated tool calls. Caller-supplied values always win. Null is a real value, not 'use the default'. Operates over serde_json::Value.
Core Metrics
| tool-loop-guard | rskit-agent | tool-arg-defaults | |
|---|---|---|---|
| Health Score | 42 | 56 | 42 |
| Total Downloads | 21 | 165 | 20 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 12 | 0 |
| Releases | 1 | 6 | 1 |
| Last Updated | 138d ago | 54d ago | 138d ago |
| Age | 4m | 3m | 4m |
Health Breakdown
tool-loop-guard
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
15
rskit-agent
Maintenance
19
Quality
11
Community
8
Popularity
3
Documentation
15
tool-arg-defaults
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
15
Technical Details
| tool-loop-guard | rskit-agent | tool-arg-defaults | |
|---|---|---|---|
| Version | 0.1.0 | 0.2.0-alpha.5 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | MIT | MIT OR Apache-2.0 |
| Dependencies | 2 | 18 | 2 |
| Crate Size | 13KB | 36KB | 9KB |
| Features | 0 | 0 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2024 | 2021 |
| MSRV | 1.74 | 1.91 | 1.74 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •rskit-agent leads with a health score of 56/100, but none of the options score above 80.