Decision Workspace
oxicuda-vision vs vit_tch vs agentic-vision
Side-by-side comparison of Rust crates
52
oxicuda-vision
experimentalv0.5.5
Vision Transformer & CLIP primitives for OxiCUDA: ViT patch embedding, multi-head self-attention, CLIP contrastive learning, FPN, RoI align, DETR decoder — pure Rust, zero CUDA SDK dependency.
39
vit_tch
experimentalv0.1.0
Vision Transformer models and building blocks for Rust using tch.
53
agentic-vision
experimentalv0.3.0
Core vision library for AgenticVision — image capture, embedding, similarity, and visual memory
Core Metrics
| oxicuda-vision | vit_tch | agentic-vision | |
|---|---|---|---|
| Health Score | 52 | 39 | 53 |
| Total Downloads | 233 | 21 | 748 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 28 |
| Releases | 13 | 1 | 16 |
| Last Updated | 57d ago | 138d ago | 224d ago |
| Age | 5m | 4m | 7m |
Health Breakdown
oxicuda-vision
Maintenance
17
Quality
14
Community
6
Popularity
3
Documentation
12
vit_tch
Maintenance
6
Quality
13
Community
5
Popularity
2
Documentation
13
agentic-vision
Maintenance
16
Quality
14
Community
10
Popularity
3
Documentation
10
Technical Details
| oxicuda-vision | vit_tch | agentic-vision | |
|---|---|---|---|
| Version | 0.5.5 | 0.1.0 | 0.3.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | MIT | MIT |
| Dependencies | 2 | 1 | 15 |
| Crate Size | 262KB | 9.8MB | 45KB |
| Features | 1 | 5 | 2 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2021 |
| MSRV | 1.85 | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •agentic-vision leads with a health score of 53/100, but none of the options score above 80.