semantica-agi /semantica
Graph-Native Infrastructure for Context and Accountable AI Systems
★ 14,617⑂ 1,728👁 64⑃ 1,535● 689▤ 24
+11
Daily
+203
Weekly
14,617
stars
1,728
forks
64
watchers
1,535
prs
689
issues
24
releases
README
Graph-Native Infrastructure for Context and Accountable AI Systems
Developer-first, knowledge infrastructure for AI, alternative to expensive enterprise platforms.
Ingest your enterprise data, extract what matters, build a Context Graph and knowledge graph (KG), and run graph analytics and causal reasoning over all of it, with full decision provenance baked in. Explainable, traceable, and trustworthy by design.
Context Management · Knowledge Modeling · Deterministic Reasoning · Ontology Management · Decision Intelligence · End-to-End Traceability
Open Source · Governed · Zero Vendor Lock-In
Polyglot Graph Storage · RDF & LPG Support · W3C Standards · Interoperable
Built for High-Stakes, Regulated Domains
bash
pip install semantica
English · Deutsch · Français · Español · Italiano · Português · العربية · اردو · हिन्दी · 中文 · 日本語 · 한국어
---
Knowledge Explorer · Context Graphs · Reasoning Engine · Decision Intelligence · Ontology Hub
▶ Watch the full platform walkthrough
---
Most AI agents run on embeddings, not meaning: similarity scores with no structure, no relationships, and no way to explain why a result came back.
Semantica is the semantic/context layer underneath your LLM, vector store, and agent framework: deterministic infrastructure (no LLM required for graph construction, reasoning, or provenance; where an LLM is used, it's optional and vendor-neutral, every major provider supported, OpenAI, Anthropic, Gemini, and more, via semantica.llms) that turns fragmented enterprise data into a structured, queryable Context Graph and knowledge graph that carries the business context, not just the data structure. Ontologies and controlled vocabularies (OWL, SHACL, SKOS) make what an entity means to your business, its definitions, relationships, and rules, as explicit as the data itself, not just its embedding.
Decision provenance and audit trails aren't the product. They fall out of that structure for free, and in domains a regulator can question, the same structure that makes your agent smarter also gives you a straight answer to "why."
[!NOTE]
System-level explainability, not foundation-model explainability. Semantica doesn't expose or reconstruct what happens inside the LLM: its internal reasoning stays opaque, like it does for any external system. Semantica explains what's outside the model: the context fed in, the decision produced, its provenance, relevant relationships, applied policies, and the full execution trail.
Who it's for:
- AI/ML platform teams shipping agents that make consequential decisions and need structured, queryable context, not just a vector index
- Enterprise data teams on Databricks, Snowflake, or SAP turning tables already in the lakehouse or warehouse into a governed, lineage-tracked knowledge graph, without exporting to a third-party SaaS
- ComplianceTop issues
#1515Integration: upstream the LangChain integration to LangChain's own docs9 comments · 2026-09-07#1521Integration: list Semantica in Qdrant's integrations directory7 comments · 2026-09-07#2018[BUG] Relationship endpoints named for a backend are still lost by every exporter but CSV6 comments · 2026-10-15#1517Integration: upstream the Agno integration to Agno's own docs/cookbook6 comments · 2026-09-07#1817[BUG] Explorer POST /api/import is additive-only; source removals stay in the session and UI edits are never persisted4 comments · 2026-09-28#1383Enhancement: optional content-integrity screening on ingested data before it becomes graph nodes4 comments · 2026-09-02#2226[BUG] Six ontology/reason CLI commands crash with AttributeError: cli.py calls methods the classes do not have3 comments · 2026-11-06#2204[BUG] ContextGraph.state_at() with an epoch timestamp is off by the machine's UTC offset3 comments · 2026-11-04
Discussions
#2263Question about `dynamic_context_traversal()`: Vector Results and Graph Expansion1 comments · 2026-11-15#631Unable to Access Dashboard Using semantica-explorer (Graph Loads Successfully)5 comments · 2026-06-15#554Is there any misconfiguration in NERExtractor? LLM method returning pattern-based output5 comments · 2026-05-14#552Query Regarding Configuration of Locally Deployed Models in Semantica Extraction Classes2 comments · 2026-05-12#347Frontend Chat interface1 comments · 2026-02-23#253Vector & Graph Store Design1 comments · 2026-01-31#175Neptune demo support for new notebook launch3 comments · 2026-01-11#173v0.2.0: Amazon Neptune, Docling Integration & Robust Extraction0 comments · 2026-01-10
Latest release
v0.7.0 v0.7.0 2026-09-22Semantica v0.7.0 Released: 2026-09-22 Tag: v0.7.0 · Compare: v0.6.8...v0.7.0 · PyPI: semantica 0.7.0 Highlights Core install is now 4x lighter — direct dependencies dropped from 44 to 22 packages, with heavy ML/NLP, visualization, document-parsing, and ingestion libraries (torch, spacy, sentence-transformers, matplotlib, faiss-cpu, python-docx, and more) moved into granular optional extras; pip install "semantica[all]" keeps the previous fully-bundled behavior. This is also the first release requiring Python 3.10+ (3.8/3.9 dropped, 3.14 not yet supported), with a committed uv.lock for repr