Decision Workspace
candding vs nabled-embeddings vs reasonkit-mem
Side-by-side comparison of Rust crates
45
candding
experimentalv0.1.0
Pure candle embeddings for Rust with no ONNX: dense, sparse, multi-vector and rerank models today, image models on the roadmap
48
nabled-embeddings
experimentalv0.0.11
Lightweight ndarray-native compute and rerank layer for embedding vectors
47
reasonkit-mem
experimentalv0.1.7
High-performance vector database & RAG memory layer - hybrid search, embeddings, RAPTOR trees, BM25 fusion, and semantic retrieval for AI systems
Core Metrics
| candding | nabled-embeddings | reasonkit-mem | |
|---|---|---|---|
| Health Score | 45 | 48 | 47 |
| Total Downloads | 10 | 74 | 3.9K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 1 | 15 |
| Releases | 1 | 1 | 8 |
| Last Updated | 6d ago | 129d ago | 256d ago |
| Age | 6d | 4m | 9m |
Health Breakdown
candding
Maintenance
13
Quality
13
Community
6
Popularity
1
Documentation
12
nabled-embeddings
Maintenance
7
Quality
15
Community
9
Popularity
2
Documentation
15
reasonkit-mem
Maintenance
11
Quality
8
Community
9
Popularity
4
Documentation
15
Technical Details
| candding | nabled-embeddings | reasonkit-mem | |
|---|---|---|---|
| Version | 0.1.0 | 0.0.11 | 0.1.7 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 OR MIT | MIT OR Apache-2.0 | Apache-2.0 |
| Dependencies | 20 | 9 | 59 |
| Crate Size | 344KB | 37KB | 320KB |
| Features | 8 | 8 | 25 |
| Yanked % | 0.0% | 0.0% | 25.0% |
| Edition | 2024 | 2024 | 2021 |
| MSRV | 1.94 | 1.92 | 1.75 |
| Owners | 1 | 2 | 1 |
Links
Quick Verdict
- •nabled-embeddings leads with a health score of 48/100, but none of the options score above 80.
- •reasonkit-mem has the most downloads (3.9K), suggesting wider adoption.