semantica took #1 on GitHub Trending overall and #1 Python with +967 stars in a day, and it builds knowledge graphs without an LLM.

semantica-agi/semantica jumped to 3,677 stars. MIT, pip install semantica, v0.6.0, 2,229 commits. The pipeline is fully deterministic, Ingest → Parse → Normalize → Split → Extract → Conflict Detection → Deduplication → Knowledge Graph → Ontology/Reasoning/Provenance/Decisions, which is exactly what gives it auditability and point-in-time snapshots for regulated use. Polyglot storage across RDF stores (Oxigraph, Blazegraph, Jena, RDF4J) and property graphs (Neo4j, FalkorDB, Apache AGE, Neptune) plus Databricks and Snowflake. README reports a 6,000× node-search improvement (24ms → 0.004ms) on a 118,000-node production graph. I've built GraphRAG on Neo4j with LangGraph, and the LLM extraction step was always the flakiest and most expensive part. A deterministic path is worth a real evaluation.