Decision Workspace
sharpebench-memory vs hippmem-eval vs kimetsu-brain
Side-by-side comparison of Rust crates
47
sharpebench-memory
experimentalv0.28.0
Three-arm memory ablation harness (baseline / retrieval / oracle): does a retrieval layer measurably improve downstream agent decisions? Significance reuses sharpebench-stats.
45
hippmem-eval
experimentalv0.4.5
Evaluation framework for HIPPMEM — corpus loading, benchmark execution, metric computation, threshold verification
61
kimetsu-brain
experimentalv2.8.0
Project + user-scope memory, hybrid retrieval (lexical + cosine), ambient context, secret redaction at ingest for kimetsu.
Core Metrics
| sharpebench-memory | hippmem-eval | kimetsu-brain | |
|---|---|---|---|
| Health Score | 47 | 45 | 61 |
| Total Downloads | 296 | 155 | 931 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 75 |
| Releases | 22 | 9 | 25 |
| Last Updated | 21d ago | 43d ago | 31d ago |
| Age | 1m | 2m | 4m |
Health Breakdown
sharpebench-memory
Maintenance
15
Quality
13
Community
6
Popularity
3
Documentation
10
hippmem-eval
Maintenance
10
Quality
12
Community
5
Popularity
3
Documentation
15
kimetsu-brain
Maintenance
17
Quality
14
Community
11
Popularity
4
Documentation
15
Technical Details
| sharpebench-memory | hippmem-eval | kimetsu-brain | |
|---|---|---|---|
| Version | 0.28.0 | 0.4.5 | 2.8.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT OR Apache-2.0 | AGPL-3.0-only | MIT OR Apache-2.0 |
| Dependencies | 4 | 8 | 16 |
| Crate Size | 52KB | 98KB | 523KB |
| Features | 0 | 0 | 3 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | — | 1.95 | 1.85 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •kimetsu-brain leads with a health score of 61/100, but none of the options score above 80.
- •sharpebench-memory, hippmem-eval are pre-1.0 — API may change.