Decision Workspace
agent-run-metadata vs agenttrace vs adk-core
Side-by-side comparison of Rust crates
40
agent-run-metadata
experimentalv0.1.0
Attach structured metadata to AI agent runs for tracing and attribution
45
agenttrace
experimentalv0.1.0
Cost + latency aggregation for LLM agent runs. Group calls into named runs, get totals, p50/p95, and per-model breakdowns. Composes with cachebench.
69
adk-core
growingv1.0.0
Core traits and types for Rust Agent Development Kit (ADK-Rust) agents, tools, sessions, and events
Core Metrics
| agent-run-metadata | agenttrace | adk-core | |
|---|---|---|---|
| Health Score | 40 | 45 | 69 |
| Total Downloads | 15 | 16 | 26.0K |
| 30d Downloads | 0 | 0 | 7.1K |
| Dependents | 0 | 0 | 580 |
| Releases | 1 | 1 | 27 |
| Last Updated | 49d ago | 64d ago | 36d ago |
| Age | 1m | 2m | 7m |
Health Breakdown
agent-run-metadata
Maintenance
10
Quality
14
Community
5
Popularity
1
Documentation
10
agenttrace
Maintenance
9
Quality
14
Community
6
Popularity
1
Documentation
15
adk-core
Maintenance
18
Quality
17
Community
14
Popularity
5
Documentation
15
Technical Details
| agent-run-metadata | agenttrace | adk-core | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.0 | 1.0.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT | MIT | Apache-2.0 |
| Dependencies | 1 | 3 | 14 |
| Crate Size | 3KB | 7KB | 93KB |
| Features | 0 | 0 | 2 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | — | 1.75 | 1.94.0 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •adk-core leads with a health score of 69/100, but none of the options score above 80.
- •adk-core is depended on by 580 crates — strongest ecosystem trust.
- •agent-run-metadata, agenttrace are pre-1.0 — API may change.