Decision Workspace
kosm-train vs scema-policy vs rlox-nn
Side-by-side comparison of Rust crates
41
kosm-train
experimentalv0.0.1
Loops that produce policies: PPO, behaviour cloning, CEM, MAP-Elites
52
scema-policy
experimentalv1.24.0
Scematica Omni — the policy layer: risk-adjusted utility over projections, with pluggable evaluators that may decline rather than guess.
50
rlox-nn
experimentalv0.3.0
Backend-agnostic neural network traits for rlox
Core Metrics
| kosm-train | scema-policy | rlox-nn | |
|---|---|---|---|
| Health Score | 41 | 52 | 50 |
| Total Downloads | 13 | 393 | 254 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 35 | 4 |
| Releases | 1 | 6 | 3 |
| Last Updated | 29d ago | 36d ago | 77d ago |
| Age | 29d | 1m | 6m |
Health Breakdown
kosm-train
Maintenance
11
Quality
13
Community
6
Popularity
1
Documentation
10
scema-policy
Maintenance
12
Quality
18
Community
9
Popularity
3
Documentation
10
rlox-nn
Maintenance
15
Quality
14
Community
8
Popularity
3
Documentation
10
Technical Details
| kosm-train | scema-policy | rlox-nn | |
|---|---|---|---|
| Version | 0.0.1 | 1.24.0 | 0.3.0 |
| Stable (≥1.0) | ✗ No | ✓ Yes | ✗ No |
| License | Apache-2.0 | MIT | MIT OR Apache-2.0 |
| Dependencies | 4 | 5 | 1 |
| Crate Size | 53KB | 31KB | 7KB |
| Features | 0 | 2 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2021 | 2021 |
| MSRV | — | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •scema-policy leads with a health score of 52/100, but none of the options score above 80.
- •kosm-train, rlox-nn are pre-1.0 — API may change.