Semantica is an open-source Python framework for building context graphs and decision intelligence layers on top of AI agents and LLM applications. It provides structured context, causal reasoning, and full decision provenance, making AI explainable and traceable.

Yes. The core library is 100% free and open source under the MIT license. No feature gating, no usage limits, no hidden tiers.

How is Semantica different from LangChain or LlamaIndex?

LangChain and LlamaIndex focus on orchestration and retrieval. Semantica adds a structured knowledge layer — context graphs, causal decision tracking, and W3C PROV-O provenance — that integrates on top of any framework.

Which AI frameworks does Semantica support?

Semantica integrates with LangGraph, CrewAI, LlamaIndex, Claude Code, AutoGen, and any Python-based agent framework, along with 100+ LLM models via LiteLLM.

What is a context graph?

A context graph is a structured, queryable knowledge graph that stores entities, relationships, and decisions made by your AI — with temporal validity and full provenance. Unlike a vector store, it understands causal relationships.

Does Semantica require a vector database?

No. Semantica works standalone. When you want hybrid graph + semantic retrieval it integrates natively with FAISS, Pinecone, Weaviate, Qdrant, Milvus, and pgvector.

What is decision provenance?

Decision provenance means every action your AI takes is stored as a first-class object with its inputs, reasoning chain, and outcome — compliant with W3C PROV-O. You can always audit why the AI did what it did.

How do I get started?

Run pip install semantica, then follow the quickstart in the docs at docs.getsemantica.ai. The core graph is up and running in under 10 lines of Python.

Semantica v0.5.0: Ontology Management, SPARQL, and the Road Ahead

Semantica v0.5.0 is now live on PyPI. This release focuses on three themes: standards compliance, schema management, and temporal intelligence. Here is what shipped and why it matters.

Ontology & Schema Management

The new OntologyManager automatically generates OWL ontologies from your context graph schema. You can import existing OWL, RDF, Turtle, or JSON-LD schemas, validate them with HermiT and Pellet consistency checkers, and export in multiple formats.

Auto-generate OWL ontologies from graph entity types and relationships.
Import existing schemas: OWL, RDF, Turtle, JSON-LD, SKOS.
HermiT and Pellet integration for consistency checking.
SHACL shape auto-generation for data validation.
Three strictness tiers: basic, standard, strict.

SPARQL Reasoning Engine

We added SPARQL as a fifth reasoning engine, enabling RDF graph queries directly over the context graph. If your team already knows SPARQL, you can now use it as a first-class way to query and reason over Semantica graphs.

sparql_reasoning.py

python

from semantica import ReasoningEngine

engine = ReasoningEngine(graph)

result = engine.sparql_query("""
    PREFIX sem: <https://semantica.ai/ontology#>
    SELECT ?entity ?decision
    WHERE {
        ?entity sem:triggeredDecision ?decision .
        ?decision sem:confidence ?conf .
        FILTER (?conf > 0.85)
    }
    ORDER BY DESC(?conf)
    LIMIT 10
""")

for row in result:
    print(row.entity, row.decision)

Temporal GraphRAG API

The new temporal_graphrag() method enables point-in-time queries over the context graph. Ask 'what was the state of the world at this timestamp?' and get a deterministic answer with full provenance.

What's Next

v0.6.0 will focus on the MCP server stability, LangGraph and CrewAI agentic framework integrations (currently in alpha), and a visual graph explorer for the REST API. We're also expanding Custom Enterprise Deployment support for teams that need dedicated infrastructure and white-glove onboarding.

NoteUpgrade with: pip install --upgrade semantica. The v0.5 migration guide is in the docs at docs.getsemantica.ai/migration/v0-5.

releasechangelogontologySPARQLGraphRAG

Back to blog