Decision Workspace
llm-agent-runtime vs agentic-memory vs wicked-memory
Side-by-side comparison of Rust crates
58
llm-agent-runtime
growingv1.76.0
Unified Tokio agent runtime -- orchestration, memory, knowledge graph, and ReAct loop in one crate
53
agentic-memory
experimentalv0.4.2
Binary graph-based memory system for AI agents
51
wicked-memory
experimentalv0.12.2
DEPRECATED: absorbed into wicked-estate v0.13+. Migrate to wicked-estate-mcp for unified memory/knowledge/estate tools.
Core Metrics
| llm-agent-runtime | agentic-memory | wicked-memory | |
|---|---|---|---|
| Health Score | 58 | 53 | 51 |
| Total Downloads | 122 | 2.1K | 140 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 32 | 4 |
| Releases | 7 | 16 | 4 |
| Last Updated | 6d ago | 224d ago | 95d ago |
| Age | 6m | 7m | 3m |
Health Breakdown
llm-agent-runtime
Maintenance
19
Quality
16
Community
6
Popularity
2
Documentation
15
agentic-memory
Maintenance
16
Quality
13
Community
10
Popularity
4
Documentation
10
wicked-memory
Maintenance
13
Quality
15
Community
8
Popularity
3
Documentation
12
Technical Details
| llm-agent-runtime | agentic-memory | wicked-memory | |
|---|---|---|---|
| Version | 1.76.0 | 0.4.2 | 0.12.2 |
| Stable (≥1.0) | ✓ Yes | ✗ No | ✗ No |
| License | MIT | MIT | MIT |
| Dependencies | 26 | 24 | 14 |
| Crate Size | 759KB | 191KB | 93KB |
| Features | 16 | 6 | 5 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | 1.85 | — | 1.85 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •llm-agent-runtime leads with a health score of 58/100, but none of the options score above 80.
- •agentic-memory has the most downloads (2.1K), suggesting wider adoption.
- •agentic-memory, wicked-memory are pre-1.0 — API may change.