Semantica provides a graph-native infrastructure for context and decision provenance, focusing on auditable decisions, provenance, and governance for AI systems. It offers context graphs, deterministic reasoning, and polyglot storage across RDF and LPG backends with enterprise connectors.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
Semantica is a Graph-Native Infrastructure for Context and Accountable AI Systems. It acts as a deterministic layer under LLMs, vector stores, and agent frameworks to provide context graphs, decision intelligence, ontologies, provenance, and audit trails. It supports multi-source ingestion, graph construction, governance, and queryable decision records with W3C PROV-O provenance.
How it works
The system builds a Context Graph and knowledge graph from multi-source ingestion (Databricks, Snowflake, files, databases, streams, etc.). It supports ontology governance (SHACL, OWL), reasoning (Rete, Datalog, SPARQL), and provenance (W3C PROV-O) with decision records as first-class graph nodes. Storage is polyglot: RDF triple stores (Blazegraph, Jena, RDF4J) and Labeled Property Graphs (Neo4j, FalkorDB, AGE, Neptune), plus vector stores, swappable without code changes. Outputs include RDF, OWL, Parquet, Cypher, JSON-LD, plus REST/MCP/CLI interfaces.
Getting started
pip install semantica
from semantica.context import ContextGraph
graph = ContextGraph(advanced_analytics=True)
decision_id = graph.record_decision(
category="vendor_selection",
scenario="Choose cloud provider for HIPAA workload",
reasoning="AWS offers BAA, mature HIPAA tooling, and existing team expertise",
outcome="selected_aws",
confidence=0.93,
)
chain = graph.trace_decision_chain(decision_id)
similar = graph.find_similar_decisions("cloud vendor", max_results=5)
impact = graph.analyze_decision_impact(decision_id)
compliant = graph.check_decision_rules({"category": "vendor_selection"})
Verify install in 5 seconds:
semantica doctor
# Python 3.11.9 pass
# semantica 0.6.0 pass
# faiss vector store pass
# Config file pass ~/.semantica/config.yaml
Recent releases
- v0.6.0 (2026-07-21): Parity across backends for named graphs and CONSTRUCT templates across Blazegraph, RDF4J, Jena
- v0.5.1 (2026-06-29): Added Apache Arrow & Feather File Ingestion via PyArrow (ArrowIngestor) for .arrow, .feather, and .ipc files
- v0.5.0 (2026-05-11): Distance Intelligence & Ontology Hub
- v0.4.0 (2026-04-08): Release notes and PyPI details for v0.4.0
- v0.3.0 (2026-03-10): First Stable Release; Python 3.8–3.12; MIT license; PyPI install guidance
Traction
1872 stars, 256 forks, 8 open issues as of the repository data.
Behind the repo
Not included in the provided facts.
Caveats
- License: MIT
- Created: 2025-06-25
- Last push: 2026-08-04
- Language: Python
- Open issues: 8
- Topics include agent-memory, ai-governance, context-graphs, provenance, SPARQL, SHACL, OWL, ontology, and more.