Decision Workspace
origin-ai vs memvid-ask-model vs zeph-llm
Side-by-side comparison of Rust crates
48
origin-ai
experimentalv0.2.1
The AI port for Origin: inference the application performs itself, behind a swappable adapter.
60
memvid-ask-model
growingv2.0.140
LLM inference module for Memvid Q&A with local and cloud model support
60
zeph-llm
experimentalv0.22.5
LLM provider abstraction with Ollama, Claude, OpenAI, and Candle backends
Core Metrics
| origin-ai | memvid-ask-model | zeph-llm | |
|---|---|---|---|
| Health Score | 48 | 60 | 60 |
| Total Downloads | 24 | 1.1K | 3.4K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 26 | 872 |
| Releases | 2 | 28 | 48 |
| Last Updated | 21d ago | 135d ago | 22d ago |
| Age | 28d | 10m | 7m |
Health Breakdown
origin-ai
Maintenance
13
Quality
15
Community
6
Popularity
2
Documentation
12
memvid-ask-model
Maintenance
13
Quality
18
Community
10
Popularity
4
Documentation
15
zeph-llm
Maintenance
18
Quality
12
Community
14
Popularity
4
Documentation
12
Technical Details
| origin-ai | memvid-ask-model | zeph-llm | |
|---|---|---|---|
| Version | 0.2.1 | 2.0.140 | 0.22.5 |
| Stable (≥1.0) | ✗ No | ✓ Yes | ✗ No |
| License | MIT | Apache-2.0 | MIT OR Apache-2.0 |
| Dependencies | 5 | 9 | 45 |
| Crate Size | 8KB | 53KB | 438KB |
| Features | 2 | 2 | 7 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2024 |
| MSRV | 1.88 | 1.85.0 | 1.98 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •memvid-ask-model leads with a health score of 60/100, but none of the options score above 80.
- •zeph-llm has the most downloads (3.4K), suggesting wider adoption.
- •zeph-llm is depended on by 872 crates — strongest ecosystem trust.
- •origin-ai, zeph-llm are pre-1.0 — API may change.