Decision Workspace
harness-rs-tools-skills vs harness-rs-core vs zeph-llm
Side-by-side comparison of Rust crates
53
harness-rs-tools-skills
experimentalv0.0.59
LLM-facing skill-authoring tool for harness-rs agents: skill_manage (create/patch/edit/delete SKILL.md). Used by the learning loop.
62
harness-rs-core
experimentalv0.0.65
Core traits and types for the harness-rs agent framework: Model, Tool, Guide, Sensor, Hook, Compactor, Skill, plus Context, World, Block, Event, FixPatch and the lifecycle events.
60
zeph-llm
experimentalv0.22.5
LLM provider abstraction with Ollama, Claude, OpenAI, and Candle backends
Core Metrics
| harness-rs-tools-skills | harness-rs-core | zeph-llm | |
|---|---|---|---|
| Health Score | 53 | 62 | 60 |
| Total Downloads | 1.2K | 6.1K | 3.4K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 1.7K | 872 |
| Releases | 55 | 65 | 48 |
| Last Updated | 38d ago | 28d ago | 22d ago |
| Age | 4m | 4m | 7m |
Health Breakdown
harness-rs-tools-skills
Maintenance
18
Quality
13
Community
6
Popularity
4
Documentation
12
harness-rs-core
Maintenance
18
Quality
12
Community
15
Popularity
5
Documentation
12
zeph-llm
Maintenance
18
Quality
12
Community
14
Popularity
4
Documentation
12
Technical Details
| harness-rs-tools-skills | harness-rs-core | zeph-llm | |
|---|---|---|---|
| Version | 0.0.59 | 0.0.65 | 0.22.5 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT | MIT OR Apache-2.0 |
| Dependencies | 4 | 9 | 45 |
| Crate Size | 9KB | 44KB | 438KB |
| Features | 0 | 0 | 7 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2024 |
| MSRV | 1.92 | 1.92 | 1.98 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •harness-rs-core leads with a health score of 62/100, but none of the options score above 80.
- •harness-rs-core is depended on by 1.7K crates — strongest ecosystem trust.