Decision Workspace
agent-run-metadata vs agenttrace vs traceflow
Side-by-side comparison of Rust crates
37
agent-run-metadata
experimentalv0.1.0
Attach structured metadata to AI agent runs for tracing and attribution
43
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.
41
traceflow
experimentalv0.1.0
Lightweight LLM call observability for Rust: latency, tokens, cost — no OpenTelemetry required
Core Metrics
| agent-run-metadata | agenttrace | traceflow | |
|---|---|---|---|
| Health Score | 37 | 43 | 41 |
| Total Downloads | 24 | 29 | 60 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 1 |
| Releases | 1 | 1 | 1 |
| Last Updated | 137d ago | 152d ago | 63d ago |
| Age | 4m | 5m | 2m |
Health Breakdown
agent-run-metadata
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
10
agenttrace
Maintenance
6
Quality
14
Community
6
Popularity
2
Documentation
15
traceflow
Maintenance
9
Quality
13
Community
7
Popularity
2
Documentation
10
Technical Details
| agent-run-metadata | agenttrace | traceflow | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.0 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT | MIT |
| Dependencies | 1 | 3 | 5 |
| Crate Size | 3KB | 7KB | 24KB |
| Features | 0 | 0 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | — | 1.75 | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •agenttrace leads with a health score of 43/100, but none of the options score above 80.
- •traceflow has the most downloads (60), suggesting wider adoption.