Decision Workspace
llm-response-cache vs lru-tokens vs tool-result-cache
Side-by-side comparison of Rust crates
37
llm-response-cache
experimentalv0.1.0
In-memory LRU cache for LLM responses keyed by request hash
44
lru-tokens
experimentalv0.1.0
LRU cache where eviction is weighted by token count, not entry count. Bound a prompt cache by tokens (or any other size unit) instead of N entries. Zero deps.
42
tool-result-cache
experimentalv0.1.0
Content-addressable LRU cache for LLM agent tool calls. Same tool, same args -> same answer, returned from memory. Optional TTL, content-addressable on (tool_name, args) with canonical-JSON keys.
Core Metrics
| llm-response-cache | lru-tokens | tool-result-cache | |
|---|---|---|---|
| Health Score | 37 | 44 | 42 |
| Total Downloads | 23 | 21 | 21 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 0 |
| Releases | 1 | 1 | 1 |
| Last Updated | 137d ago | 146d ago | 138d ago |
| Age | 4m | 4m | 4m |
Health Breakdown
llm-response-cache
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
10
lru-tokens
Maintenance
6
Quality
15
Community
6
Popularity
2
Documentation
15
tool-result-cache
Maintenance
6
Quality
14
Community
5
Popularity
2
Documentation
15
Technical Details
| llm-response-cache | lru-tokens | tool-result-cache | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.0 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT OR Apache-2.0 | MIT OR Apache-2.0 |
| Dependencies | 2 | 0 | 2 |
| Crate Size | 4KB | 8KB | 17KB |
| Features | 0 | 0 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | — | 1.74 | 1.74 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •lru-tokens leads with a health score of 44/100, but none of the options score above 80.
- •llm-response-cache has the most downloads (23), suggesting wider adoption.