Decision Workspace
newt-inference vs ikigai-llm vs woollama-engine
Side-by-side comparison of Rust crates
53
newt-inference
experimentalv0.7.5
Newt-Agent inference layer: backend trait + local Ollama/vLLM + provider-plugin host
55
ikigai-llm
experimentalv0.13.0
Flexible LLM inference as ikigai ROC resources: urn:llm:ask (a facade grammar) dispatches to pluggable backends. Slice 0 ships an OpenAI-compatible REST backend covering Ollama / vLLM / llama.cpp-server / mlx_lm.server / LM Studio.
50
woollama-engine
experimentalv0.12.0
The pure-Rust woollama engine (no PyO3): inferencer registry, complete/stream, the recipe<->tool orchestrate loop. Consumed by the woollama-core wheel and the woollamad daemon (woollama-server crate).
Core Metrics
| newt-inference | ikigai-llm | woollama-engine | |
|---|---|---|---|
| Health Score | 53 | 55 | 50 |
| Total Downloads | 407 | 1.2K | 306 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 22 | 71 | 15 |
| Releases | 5 | 17 | 10 |
| Last Updated | 72d ago | 1d ago | 53d ago |
| Age | 4m | 3m | 3m |
Health Breakdown
newt-inference
Maintenance
15
Quality
14
Community
9
Popularity
3
Documentation
12
ikigai-llm
Maintenance
19
Quality
12
Community
10
Popularity
4
Documentation
10
woollama-engine
Maintenance
16
Quality
12
Community
9
Popularity
3
Documentation
10
Technical Details
| newt-inference | ikigai-llm | woollama-engine | |
|---|---|---|---|
| Version | 0.7.5 | 0.13.0 | 0.12.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | MIT OR Apache-2.0 | MIT |
| Dependencies | 24 | 10 | 8 |
| Crate Size | 81KB | 76KB | 32KB |
| Features | 5 | 0 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.88 | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •ikigai-llm leads with a health score of 55/100, but none of the options score above 80.