rust-kgdb 0.6.21 → 0.6.22

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +17 -0
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -531,6 +531,23 @@ console.log('Similar:', similar)
531
531
  | **Vanilla LLM** | 0% | Hallucinated predicates, markdown in SPARQL |
532
532
  | **HyperMind** | 86.4% | Schema injection, typed tools, audit trail |
533
533
 
534
+ ### AI Framework Comparison
535
+
536
+ | Framework | Type Safety | Schema Aware | Symbolic Execution | Success Rate |
537
+ |-----------|-------------|--------------|-------------------|--------------|
538
+ | **HyperMind** | ✅ Yes | ✅ Yes | ✅ Yes | **86.4%** |
539
+ | LangChain | ❌ No | ❌ No | ❌ No | ~20-40%* |
540
+ | AutoGPT | ❌ No | ❌ No | ❌ No | ~10-25%* |
541
+ | DSPy | ⚠️ Partial | ❌ No | ❌ No | ~30-50%* |
542
+
543
+ *Estimated from public benchmarks on structured data tasks
544
+
545
+ **Why HyperMind Wins**:
546
+ - **Type Safety**: Tools have typed signatures (Query → BindingSet), invalid combinations rejected
547
+ - **Schema Awareness**: LLM sees your actual data structure, can only reference real properties
548
+ - **Symbolic Execution**: Queries run against real database, not LLM imagination
549
+ - **Audit Trail**: Every answer has cryptographic hash for reproducibility
550
+
534
551
  ---
535
552
 
536
553
  ## W3C Standards Compliance
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "rust-kgdb",
3
- "version": "0.6.21",
3
+ "version": "0.6.22",
4
4
  "description": "Production-grade Neuro-Symbolic AI Framework with Schema-Aware GraphDB, Context Theory, and Memory Hypergraph: +86.4% accuracy over vanilla LLMs. Features Schema-Aware GraphDB (auto schema extraction), BYOO (Bring Your Own Ontology) for enterprise, cross-agent schema caching, LLM Planner for natural language to typed SPARQL, ProofDAG with Curry-Howard witnesses. High-performance (2.78µs lookups, 35x faster than RDFox). W3C SPARQL 1.1 compliant.",
5
5
  "main": "index.js",
6
6
  "types": "index.d.ts",