Decision Workspace
cqs vs semtree-embed vs semtree-core
Side-by-side comparison of Rust crates
49
cqs
growingv1.54.0
Code intelligence and RAG for AI agents. Semantic search, call graphs, impact analysis, type dependencies, and smart context assembly — in single tool calls. 54 languages + L5X/L5K PLC exports. 69.8% R@5 / 43.6% R@1 / 83.5% R@20 on v3.v2 dual-judge code-search (218 queries, EmbeddingGemma-300m default with per-category SPLADE α; 2026-07-03 snapshot, scoring unchanged through v1.54.0). Daemon mode (3-19ms queries). MCP server (`cqs mcp`, 30 read tools, full input+output schemas). Local-first, GPU-accelerated.
56
semtree-embed
experimentalv0.5.0
Embedding trait and backends (fastembed, openai)
55
semtree-core
experimentalv0.5.0
Core types for semtree: Language, Span, Node, Chunk
Core Metrics
| cqs | semtree-embed | semtree-core | |
|---|---|---|---|
| Health Score | 49 | 56 | 55 |
| Total Downloads | 3.0K | 556 | 747 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 26 | 37 |
| Releases | 127 | 6 | 6 |
| Last Updated | 98d ago | 63d ago | 63d ago |
| Age | 8m | 6m | 6m |
Health Breakdown
cqs
Maintenance
14
Quality
13
Community
6
Popularity
4
Documentation
12
semtree-embed
Maintenance
16
Quality
15
Community
10
Popularity
3
Documentation
12
semtree-core
Maintenance
16
Quality
14
Community
10
Popularity
3
Documentation
12
Technical Details
| cqs | semtree-embed | semtree-core | |
|---|---|---|---|
| Version | 1.54.0 | 0.5.0 | 0.5.0 |
| Stable (≥1.0) | ✓ Yes | ✗ No | ✗ No |
| License | MIT | MIT | MIT |
| Dependencies | 121 | 7 | 3 |
| Crate Size | 7.1MB | 29KB | 7KB |
| Features | 67 | 4 | 0 |
| Yanked % | 0.8% | 0.0% | 0.0% |
| Edition | 2021 | 2024 | 2024 |
| MSRV | 1.96 | 1.88 | 1.88 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •semtree-embed leads with a health score of 56/100, but none of the options score above 80.
- •cqs has the most downloads (3.0K), suggesting wider adoption.
- •semtree-embed, semtree-core are pre-1.0 — API may change.