Decision Workspace
agenttrace vs token-budget-pool vs iron_cost
Side-by-side comparison of Rust crates
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.
48
token-budget-pool
experimentalv0.1.0
Shared token + dollar budget across concurrent LLM tasks. Thread-safe, returns BudgetExceeded when a record would push past a cap. Zero deps.
47
iron_cost
experimentalv0.3.0
Budget tracking and cost enforcement for Iron Cage AI agents
Core Metrics
| agenttrace | token-budget-pool | iron_cost | |
|---|---|---|---|
| Health Score | 45 | 48 | 47 |
| Total Downloads | 16 | 21 | 452 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 9 |
| Releases | 1 | 1 | 2 |
| Last Updated | 64d ago | 58d ago | 209d ago |
| Age | 2m | 1m | 7m |
Health Breakdown
agenttrace
Maintenance
9
Quality
14
Community
6
Popularity
1
Documentation
15
token-budget-pool
Maintenance
10
Quality
15
Community
6
Popularity
2
Documentation
15
iron_cost
Maintenance
9
Quality
14
Community
9
Popularity
3
Documentation
12
Technical Details
| agenttrace | token-budget-pool | iron_cost | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.0 | 0.3.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT OR Apache-2.0 | MIT |
| Dependencies | 3 | 0 | 9 |
| Crate Size | 7KB | 8KB | 37KB |
| Features | 0 | 0 | 4 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.75 | 1.74 | 1.70 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •token-budget-pool leads with a health score of 48/100, but none of the options score above 80.
- •iron_cost has the most downloads (452), suggesting wider adoption.