Decision Workspace
tool-call-trace vs agent-replay-trace vs amberfork-model
Side-by-side comparison of Rust crates
37
tool-call-trace
experimentalv0.1.0
Record and replay tool call traces for LLM agents
37
agent-replay-trace
experimentalv0.1.0
Load and step through JSONL agent traces
63
amberfork-model
experimentalv1.0.0
Canonical Run/Step trajectory model and DiffResult schema for amberfork (the frozen contract every crate reads).
Core Metrics
| tool-call-trace | agent-replay-trace | amberfork-model | |
|---|---|---|---|
| Health Score | 37 | 37 | 63 |
| Total Downloads | 25 | 23 | 310 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 29 |
| Releases | 1 | 1 | 3 |
| Last Updated | 138d ago | 138d ago | 35d ago |
| Age | 4m | 4m | 3m |
Health Breakdown
tool-call-trace
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
10
agent-replay-trace
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
10
amberfork-model
Maintenance
17
Quality
18
Community
10
Popularity
3
Documentation
15
Technical Details
| tool-call-trace | agent-replay-trace | amberfork-model | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.0 | 1.0.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT | MIT | MIT |
| Dependencies | 1 | 1 | 2 |
| Crate Size | 3KB | 6KB | 13KB |
| Features | 0 | 0 | 1 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | — | — | 1.85 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •amberfork-model leads with a health score of 63/100, but none of the options score above 80.
- •tool-call-trace, agent-replay-trace are pre-1.0 — API may change.