Decision Workspace
red-queen-llm vs split-brain-harness vs atlas-detect
Side-by-side comparison of Rust crates
35
red-queen-llm
experimentalv0.1.0
LLM safety domain for Red Queen
49
split-brain-harness
experimentalv1.6.0
Soul-injected two-stage LLM telemetry pipeline. Wraps any LLM with affective/intent/cognitive analysis, deterministic verification, and a Stage 0 deobfuscation normalizer. Drop-in OpenAI-compatible proxy.
43
atlas-detect
experimentalv0.1.0
MITRE ATLAS technique detection for LLM and AI agent security. Detects prompt injection, jailbreaks, credential exfiltration, model extraction, and 90+ other AI-specific attack techniques.
Core Metrics
| red-queen-llm | split-brain-harness | atlas-detect | |
|---|---|---|---|
| Health Score | 35 | 49 | 43 |
| Total Downloads | 117 | 135 | 2.2K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 1 | 0 | 0 |
| Releases | 1 | 7 | 1 |
| Last Updated | 207d ago | 6d ago | 180d ago |
| Age | 6m | 3m | 6m |
Health Breakdown
red-queen-llm
Maintenance
5
Quality
12
Community
6
Popularity
2
Documentation
10
split-brain-harness
Maintenance
19
Quality
11
Community
6
Popularity
3
Documentation
10
atlas-detect
Maintenance
5
Quality
15
Community
6
Popularity
4
Documentation
13
Technical Details
| red-queen-llm | split-brain-harness | atlas-detect | |
|---|---|---|---|
| Version | 0.1.0 | 1.6.0 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✓ Yes | ✗ No |
| License | AGPL-3.0-or-later | MIT | Apache-2.0 |
| Dependencies | 14 | 19 | 4 |
| Crate Size | 26KB | 216KB | 20KB |
| Features | 0 | 4 | 2 |
| Yanked % | 0.0% | 14.3% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | — | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •split-brain-harness leads with a health score of 49/100, but none of the options score above 80.
- •atlas-detect has the most downloads (2.2K), suggesting wider adoption.
- •red-queen-llm, atlas-detect are pre-1.0 — API may change.