Decision Workspace
agent-witness vs abk vs is-ai-agent
Side-by-side comparison of Rust crates
38
agent-witness
experimentalv0.0.6
The audit trail for AI coding agents — check what a Claude Code session actually did, not just what it said
60
abk
experimentalv0.20.0
Agent Builder Kit - Complete modular agent building blocks with feature-gated modules
60
is-ai-agent
experimentalv0.6.0
Detect whether a CLI is being invoked by an AI coding agent, and identify which one.
Core Metrics
| agent-witness | abk | is-ai-agent | |
|---|---|---|---|
| Health Score | 38 | 60 | 60 |
| Total Downloads | 63 | 7.8K | 13.0K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 374 | 10 |
| Releases | 3 | 199 | 7 |
| Last Updated | 90d ago | 6d ago | 16d ago |
| Age | 3m | 11m | 5m |
Health Breakdown
agent-witness
Maintenance
9
Quality
11
Community
6
Popularity
2
Documentation
10
abk
Maintenance
19
Quality
13
Community
13
Popularity
5
Documentation
10
is-ai-agent
Maintenance
18
Quality
15
Community
9
Popularity
5
Documentation
13
Technical Details
| agent-witness | abk | is-ai-agent | |
|---|---|---|---|
| Version | 0.0.6 | 0.20.0 | 0.6.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | MIT OR Apache-2.0 | MIT OR Apache-2.0 |
| Dependencies | 10 | 42 | 0 |
| Crate Size | 132KB | 377KB | 28KB |
| Features | 0 | 18 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | — | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •abk leads with a health score of 60/100, but none of the options score above 80.
- •is-ai-agent has the most downloads (13.0K), suggesting wider adoption.
- •abk is depended on by 374 crates — strongest ecosystem trust.