### The Context and Accountability Layer for AI Agents
> Semantica is the Context and Accountability Layer for AI agents: context graphs, decision intelligence, explainable reasoning, and policy governance, with a permanent audit trail behind every decision.
>
> It's the intelligence category **Palantir** built for the enterprise, delivered **100% open source** and self-hostable, with zero black boxes and zero vendor lock-in, from startup to Fortune 500, without the seven-figure contract.
**Decision Intelligence · Context Management · Deterministic Reasoning · Traceability**
**Open Source · Auditable · Governed · Self-Hostable**
**Polyglot Graph Storage**
[](https://github.com/semantica-agi/semantica) [](https://pypi.org/project/semantica/) [](https://pepy.tech/project/semantica) [](https://www.python.org/) [](https://opensource.org/licenses/MIT) [](https://github.com/semantica-agi/semantica/actions) [](https://deepwiki.com/semantica-agi/semantica)
[](https://getsemantica.ai/) [](https://docs.getsemantica.ai/) [](https://discord.gg/sV34vps5hH) [](https://x.com/BuildSemantica) [](https://www.youtube.com/watch?v=QfnNZg4-dZA) [](CHANGELOG.md)
---
> Most AI agents act without a trail. They store embeddings, not meaning: context that can't be explained, decisions that can't be audited. Regulators, auditors, and enterprise risk teams all ask the same question: **can you prove what your AI did and why?**
>
> Semantica answers that question. It sits alongside your LLM, vector store, and agent framework as a dedicated context and accountability layer, adding structured intelligence, causal reasoning, and a full audit trail to every decision your agents make. Built for teams running AI agents in production, especially in healthcare, finance, legal, and government, where every decision must be explainable and defensible.
**What Semantica gives you:**
- **Context Graphs:** A structured, queryable graph of everything your agent knows, decides, and reasons about
- **Decision Intelligence:** Every decision is a first-class object: traceable, searchable by precedent, and causally linked
- **AI Governance & Ontology:** SHACL constraints, conflict detection, compliance rules, OWL generation, and SKOS vocabulary management with a visual editor
- **Full Auditability:** W3C PROV-O provenance on every fact, with audit trails exportable to JSON, CSV, or RDF
- **Deterministic Reasoning:** Forward chaining, Rete network, Datalog, and SPARQL with fully explainable paths, not black boxes
- **Knowledge Pipeline:** Multi-source ingestion, entity-aware chunking, and semantic deduplication with provenance-preserving merges
- **Polyglot Graph Storage:** Native support for both RDF (Blazegraph, Apache Jena, Eclipse RDF4J via SPARQL) and Labeled Property Graphs (Neo4j, FalkorDB, Apache AGE, AWS Neptune via Cypher), plus vector stores, all swappable without touching your code
- **Flexible Storage & Visualization:** Swap storage backends freely; explore it all in an interactive browser workbench
- **Drop-in Integrations:** Native Agno support, a full-featured MCP server, a comprehensive CLI, a REST API, and plugins across major editors
---
**[Quick Start](#quick-start)** · **[Architecture](ARCHITECTURE.md)** · **[Why Semantica](#why-semantica)** · **[Context Graphs](#context-graphs)** · **[Decision Intelligence](#decision-intelligence)** · **[Module Reference](#module-reference)** · **[Recipes](#recipes)** · **[CLI](#cli)** · **[Integrations](#integrations)** · **[Performance](#performance)** · **[Install](#installation)**
---
## See It in Action
**[Watch the full platform walkthrough →](https://www.youtube.com/watch?v=QfnNZg4-dZA)**
*Knowledge Explorer · Context Graphs · Reasoning Engine · Decision Intelligence · Ontology Hub*
---
## Quick Start
```bash
pip install semantica
```
```python
from semantica.context import ContextGraph
graph = ContextGraph(advanced_analytics=True)
# Every agent decision becomes a queryable, auditable knowledge node
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,
)
# Ask "why did this happen?" and get a real, structured answer
chain = graph.trace_decision_chain(decision_id) # full causal ancestry
similar = graph.find_similar_decisions("cloud vendor", max_results=5) # precedents
impact = graph.analyze_decision_impact(decision_id) # downstream influence map
compliant = graph.check_decision_rules({"category": "vendor_selection"}) # policy gate
```
**Verify your install in 5 seconds:**
```bash
semantica doctor
# Python 3.11.9 pass
# semantica 0.5.1 pass
# faiss vector store pass
# Config file pass ~/.semantica/config.yaml
```
If Semantica solves a real problem for you, a star helps others find it.
**[⭐ Star on GitHub](https://github.com/semantica-agi/semantica)** · **[Join Discord](https://discord.gg/sV34vps5hH)**
---
## Architecture
The full data pipeline and decision intelligence lifecycle are documented with Mermaid flowcharts in **[ARCHITECTURE.md](ARCHITECTURE.md)**:
- [Full data pipeline](ARCHITECTURE.md#full-data-pipeline): all sources → ingest → parse → normalize → split → extract → deduplication → KG → storage → export
- [Decision intelligence lifecycle](ARCHITECTURE.md#decision-intelligence-lifecycle): record → link → query → govern → audit
**→ [View architecture →](ARCHITECTURE.md)**
Every component is independently importable. Use one module or all of them.
---
## Why Semantica
| | Vector DB + RAG | Plain LLM Memory | **Semantica** |
| --- | --- | --- | --- |
| **Recall method** | Embedding similarity | Token window | Graph traversal + semantic search |
| **Decision history** | Not stored | Not stored | First-class queryable objects |
| **Provenance** | None | None | W3C PROV-O, source-linked |
| **Reasoning** | None | Black box | Forward chain, Rete, Datalog, SPARQL |
| **Conflict detection** | Silent overwrite | Silent overwrite | Detected, flagged, resolved |
| **Time travel** | No | No | Point-in-time graph snapshots |
| **Compliance export** | None | None | PROV-O, SHACL, OWL, RDF |
| **Policy enforcement** | None | None | Built-in rule engine + SHACL |
| **Entity resolution** | No | No | Blocking + semantic deduplication |
| **Multi-agent context** | Separate per agent | Separate per agent | Single shared intelligence layer |
Semantica complements your existing stack rather than replacing it. Keep your LLM, vector store, and agent framework exactly as they are. Semantica sits alongside them as the accountability and intelligence layer, adding structured decision records, causal reasoning, W3C PROV-O provenance, ontology governance, conflict detection, and compliance-grade audit trails. The reasoning engines, KG construction, and provenance layer are fully deterministic; no LLM is required to use them.
---
## Context Graphs
A Context Graph is the structured memory layer that traditional RAG is missing. Instead of flat embeddings that answer *"what is similar?"*, a Context Graph answers *"what is connected, why, and how?"*
Every entity, relationship, decision, and fact is a first-class node, queryable by graph traversal and neighbor expansion. Entities link to source documents. Decisions link to evidence and consequences. Facts carry full provenance. Conflicts are detected, not silently overwritten.
```python
from semantica.context import ContextGraph, AgentContext
from semantica.vector_store import VectorStore
graph = ContextGraph(advanced_analytics=True)
# Add nodes with typed properties
graph.add_node("acme_corp", "Organization", name="Acme Corp", industry="SaaS")
graph.add_node("alice_chen", "Person", name="Alice Chen", role="CTO")
graph.add_node("contract_001", "Contract", value=2_400_000, currency="USD")
# Add typed, weighted edges (extra kwargs become edge metadata)
graph.add_edge("alice_chen", "acme_corp", edge_type="works_for", since="2019-03-01")
graph.add_edge("acme_corp", "contract_001", edge_type="party_to", signed="2024-01-15")
# BFS traversal - hop through the graph from any node
neighbors = graph.get_neighbors("acme_corp", hops=2)
# Point-in-time snapshot - the graph as it existed on any past date
snapshot = graph.state_at("2024-01-01")
# AgentContext - high-level API for agent memory workflows
vs = VectorStore(backend="faiss")
ctx = AgentContext(vector_store=vs, knowledge_graph=graph)
ctx.store("Alice approved the Acme renewal in Q1 2024", conversation_id="conv_001")
retrieved = ctx.retrieve("who approved the Acme contract?")
```
**Why graph over embeddings:**
- Traversal finds connections embeddings miss, including a person 3 hops from a contract
- Every node carries provenance so you can always ask *"where did this come from?"*
- Conflicts are detected and flagged before they corrupt your knowledge base
- Point-in-time snapshots let you replay history without reprocessing
---
## Decision Intelligence
Decision Intelligence turns every AI choice from an ephemeral inference into a permanent, auditable, queryable record. It answers *"what did your AI decide, why, and what happened next?"* The question regulators and enterprise risk teams are asking with increasing urgency.
In Semantica, a decision is not a log line. It is a first-class graph node with a full lifecycle. In regulated domains, every AI decision must be traceable to a source and defensible to an auditor: `record_decision()` creates a permanent, structured record exportable as W3C PROV-O, the format most compliance frameworks accept for regulator submission.
```
record_decision() → stored as a graph node with full structured context
add_causal_relationship() → linked to upstream causes and downstream effects
find_similar_decisions() → semantic precedent search across all past decisions
trace_decision_chain() → full causal ancestry back to root causes
analyze_decision_impact() → downstream influence map - everything this decision affected
check_decision_rules() → policy compliance gate against configurable rule sets
export / audit trail → W3C PROV-O, CSV, or JSON for regulator submission
```
```python
from semantica.context import ContextGraph
graph = ContextGraph(advanced_analytics=True)
# Record decisions with full structured context
app_id = graph.record_decision(
category="credit_application",
scenario="Personal loan, $85k income, 31% DTI, 3yr employment",
reasoning="Income meets threshold; employment stable; no adverse credit events",
outcome="proceed_to_underwriting",
confidence=0.88,
metadata={"applicant_id": "A-7291"},
)
uw_id = graph.record_decision(
category="loan_underwriting",
scenario="Underwriting review for A-7291",
reasoning="DTI within policy; clean 36-month credit history",
outcome="approved",
confidence=0.94,
)
rate_id = graph.record_decision(
category="interest_rate",
scenario="Rate assignment for approved loan A-7291",
outcome="rate_set_8.9pct",
reasoning="Prime + 2.4% based on risk tier B2",
confidence=0.99,
)
# Build the auditable causal chain
graph.add_causal_relationship(app_id, uw_id, relationship_type="triggers")
graph.add_causal_relationship(uw_id, rate_id, relationship_type="enables")
# Query the intelligence
chain = graph.trace_decision_chain(rate_id)
similar = graph.find_similar_decisions("personal loan approval, 31% DTI", max_results=5)
impact = graph.analyze_decision_impact(uw_id)
compliant = graph.check_decision_rules({"category": "loan_underwriting", "confidence": 0.94})
insights = graph.get_decision_insights()
```
---
## Module Reference
Semantica is a full platform. Every module is independently importable and composable. Below are working examples for each.
### `semantica.ingest`: Multi-Source Ingestion
Ingest from files, web, databases, APIs, streams, email, Git repos, Parquet, Snowflake, or MCP servers, all through a unified interface.
```python
from semantica.ingest import FileIngestor, WebIngestor, ParquetIngestor, DBIngestor
# Ingest an entire directory of contracts (PDF, DOCX, HTML, TXT)
docs = FileIngestor().ingest_directory("./contracts/", recursive=True)
# Ingest live web content with robots.txt compliance
pages = WebIngestor().ingest_url("https://example.com/reports/annual-2024.html")
# Ingest structured data from Parquet with Snappy compression
records = ParquetIngestor().ingest("./data/transactions.parquet")
# Ingest from a SQL database - specify which tables to pull
rows = DBIngestor().ingest_database(
connection_string="postgresql://user:pass@localhost/mydb",
include_tables=["customer_events"],
max_rows_per_table=50_000,
)
```
**Supported sources:** Local files (PDF, DOCX, PPTX, HTML, TXT, CSV, JSON, YAML, Excel, XML) · Web pages · RSS/Atom feeds · REST APIs · Databases (PostgreSQL, MySQL, SQLite, Oracle, SQL Server) · Parquet datasets · Snowflake · Git repositories · Email (IMAP/POP3) · Message streams (Kafka, RabbitMQ, Kinesis, Pulsar) · MCP resources
---
### `semantica.semantic_extract`: NER, Relations, Events, Triplets
Extract structured knowledge from raw text in one pass.
```python
from semantica.semantic_extract import (
NamedEntityRecognizer,
RelationExtractor,
EventDetector,
TripletExtractor,
)
text = """
Anthropic CEO Dario Amodei announced a $7.3B Series E funding round in partnership
with Google and Spark Capital, valuing the company at $61.5B as of Q4 2024.
"""
# Named entity recognition with confidence thresholding
ner = NamedEntityRecognizer(confidence_threshold=0.7)
entities = ner.extract_entities(text)
# → [Entity(name="Dario Amodei", type="PERSON"), Entity(name="Anthropic", type="ORG"),
# Entity(name="Google", type="ORG"), Entity(name="$7.3B", type="MONEY"), ...]
# Relationship extraction - bidirectional support
rel_extractor = RelationExtractor(confidence_threshold=0.6, bidirectional=True)
relations = rel_extractor.extract_relations(text, entities=entities)
# → [Relation(subject="Dario Amodei", predicate="ceo_of", object="Anthropic"),
# Relation(subject="Anthropic", predicate="raised", object="$7.3B Series E"), ...]
# Event detection with temporal processing
events = EventDetector(extract_participants=True, extract_time=True).detect_events(text)
# → [Event(type="FUNDING", participants=["Anthropic","Google","Spark Capital"],
# amount="$7.3B", date="Q4 2024")]
# RDF triplets with optional provenance metadata
triplets = TripletExtractor(include_temporal=True, include_provenance=True).extract_triplets(text)
# → [("Anthropic", "valuation", "$61.5B"), ("Dario Amodei", "is_ceo_of", "Anthropic"), ...]
```
---
### `semantica.kg`: Knowledge Graph Construction & Analysis
Build a production knowledge graph from documents and run graph algorithms over it.
```python
from semantica.ingest import FileIngestor
from semantica.kg import (
GraphBuilder,
GraphAnalyzer,
CentralityCalculator,
CommunityDetector,
PathFinder,
LinkPredictor,
BiTemporalFact,
)
from datetime import datetime
# Build KG - merge duplicate entities, track temporal edges
sources = FileIngestor().ingest_directory("./contracts/", recursive=True)
kg = GraphBuilder(merge_entities=True, enable_temporal=True).build(sources)
# Graph analytics
analyzer = GraphAnalyzer()
analysis = analyzer.analyze_graph(kg) # full graph metrics
centrality = CentralityCalculator()
degree = centrality.calculate_degree_centrality(kg) # most-connected entities
betweenness = centrality.calculate_betweenness_centrality(kg)
communities = CommunityDetector().detect_communities(kg, method="louvain") # natural clusters
path = PathFinder().find_shortest_path(kg, "alice_chen", "contract_001")
predictions = LinkPredictor().predict_links(kg, top_k=10) # relationship predictions
# Bi-temporal facts - track valid time vs. recorded time independently
fact = BiTemporalFact(
valid_from=datetime(2024, 3, 1),
valid_until=datetime(2025, 1, 1),
recorded_at=datetime(2024, 3, 5),
)
```
---
### `semantica.reasoning`: Forward Chaining, Rete, Datalog, SPARQL
Run explainable rule-based inference, not a black box.
```python
from semantica.reasoning import ReteEngine, Rule, Fact, RuleType
rete = ReteEngine()
rete.build_network([
Rule(
rule_id="aml_flag",
name="Flag high-risk transactions",
conditions=[
{"field": "amount", "operator": ">", "value": 10_000},
{"field": "country", "operator": "in", "value": ["IR", "KP", "SY"]},
],
conclusion="flag_for_compliance_review",
rule_type=RuleType.IMPLICATION,
),
Rule(
rule_id="velocity_check",
name="Flag rapid sequential transfers",
conditions=[
{"field": "transfers_in_1h", "operator": ">", "value": 5},
{"field": "total_amount", "operator": ">", "value": 50_000},
],
conclusion="flag_velocity_breach",
rule_type=RuleType.IMPLICATION,
),
])
rete.add_fact(Fact("tx_001", "transaction", [{"amount": 15_000, "country": "IR"}]))
flagged = rete.match_patterns()
# → [{"rule": "aml_flag", "matched_facts": ["tx_001"], "conclusion": "flag_for_compliance_review"}]
```
```python
# Recursive Datalog - natural language for graph queries
from semantica.reasoning import DatalogReasoner
engine = DatalogReasoner()
engine.add_fact("parent(tom, bob)")
engine.add_fact("parent(bob, ann)")
engine.add_fact("parent(ann, pat)")
engine.add_rule("ancestor(X, Y) :- parent(X, Y).")
engine.add_rule("ancestor(X, Z) :- parent(X, Y), ancestor(Y, Z).")
ancestors = engine.query("ancestor(tom, ?X)")
# → [{"X": "bob"}, {"X": "ann"}, {"X": "pat"}]
```
```python
# Explainable reasoning - trace the path, not just the answer
from semantica.reasoning import ExplanationGenerator, Reasoner
reasoner = Reasoner()
result = reasoner.infer(kg, rules=[...])
explainer = ExplanationGenerator()
explanation = explainer.generate(result)
# → Explanation(conclusion="...", steps=[ReasoningStep(...)], justification=Justification(...))
```
---
### `semantica.vector_store`: Hybrid & Filtered Semantic Search
Drop-in vector store with multiple backends, hybrid search, and decision-aware retrieval.
```python
from semantica.vector_store import VectorStore, HybridSearch
# Works with FAISS, Qdrant, Weaviate, Milvus, Pinecone, PgVector, or in-memory
vs = VectorStore(backend="qdrant", dimension=1536)
# Store a decision with scenario description and outcome
vs.store_decision(
scenario="Personal loan A-7291, $85k income, 31% DTI, 3yr employment",
outcome="approved",
confidence=0.94,
category="loan_underwriting",
)
# Semantic similarity search
results = vs.search(
query="personal loan approval with low DTI",
limit=10,
)
# Hybrid search - dense + sparse retrieval in one pass with RRF fusion
hs = HybridSearch(vector_store=vs)
hits = hs.search("high-risk transactions 2024")
# Explain why a decision was retrieved
explanation = vs.explain_decision(results[0]["id"])
```
---
### `semantica.split`: GraphRAG-Native Document Chunking
KG-aware splitting that preserves entity boundaries, relation triplets, and ontology concepts, essential for GraphRAG pipelines.
```python
from semantica.split import TextSplitter, EntityAwareChunker, RelationAwareChunker
text = open("contracts/master_agreement.txt").read()
# Standard recursive chunking
chunks = TextSplitter(method="recursive", chunk_size=1000, chunk_overlap=200).split(text)
# Entity-aware chunking - never splits a named entity across chunks (GraphRAG)
chunks = TextSplitter(method="entity_aware", ner_method="llm", chunk_size=1000).split(text)
# Relation-aware chunking - preserves (subject, predicate, object) triplets intact
chunks = RelationAwareChunker(chunk_size=1000, preserve_triplets=True).chunk(text)
# Graph-based chunking - uses centrality to find natural community boundaries
chunks = TextSplitter(method="graph_based", chunk_size=1000).split(text)
# Hierarchical chunking - multi-level (section → paragraph → sentence)
chunks = TextSplitter(method="hierarchical", levels=["section", "paragraph"]).split(text)
```
**Supported methods:** `recursive` · `token` · `sentence` · `paragraph` · `semantic_transformer` · `entity_aware` · `relation_aware` · `graph_based` · `ontology_aware` · `hierarchical` · `community_detection` · `centrality_based` · `llm`
---
### `semantica.provenance`: W3C PROV-O Lineage
Every fact is linked to its source. No black boxes, no mystery outputs.
```python
from semantica.provenance import ProvenanceManager
prov = ProvenanceManager(storage_path="./provenance.db")
# Track where every entity came from
prov.track_entity(
entity_id="acme_corp",
source="contracts/acme_master_agreement_2024.pdf",
metadata={"page": 1, "confidence": 0.97, "extractor": "NamedEntityRecognizer"},
)
prov.track_relationship(
relationship_id="alice_works_for_acme",
source_entity_id="alice_chen",
target_entity_id="acme_corp",
source="hr_records/employees_q1_2024.csv",
)
# Answer "where did this come from?"
lineage = prov.get_lineage("acme_corp")
trail = prov.trace_lineage("alice_chen") # full ancestor chain
entry = prov.get_provenance("acme_corp")
```
---
### `semantica.ontology`: OWL Generation, SHACL Validation
Generate ontologies from data, validate shapes, and manage your vocabulary.
```python
from semantica.ontology import OntologyGenerator, OntologyValidator
data = {
"entities": [
{"id": "acme_corp", "type": "Organization", "industry": "SaaS", "founded": 2012},
{"id": "alice_chen", "type": "Person", "role": "CTO", "since": 2019},
],
"relationships": [
{"source": "alice_chen", "target": "acme_corp", "type": "works_for"},
],
}
gen = OntologyGenerator(base_uri="https://semantica.dev/ontology/")
ontology = gen.generate_ontology(data)
classes = gen.infer_classes(data)
props = gen.infer_properties(data, classes)
optimized = gen.optimize_ontology(ontology)
# Validate against SHACL shapes
validator = OntologyValidator()
report = validator.validate(ontology)
# → ValidationResult(conforms=True, errors=[], warnings=[])
```
---
### `semantica.conflicts`: Conflict Detection & Resolution
Detect and resolve conflicting facts from multiple sources before they corrupt your knowledge base.
```python
from semantica.conflicts import ConflictDetector, ConflictResolver, SourceTracker
entities_from_source_a = [
{"id": "alice_chen", "role": "CTO", "salary": 250_000, "start_date": "2019-03-01"},
]
entities_from_source_b = [
{"id": "alice_chen", "role": "VP Eng", "salary": 275_000, "start_date": "2019-03-01"},
]
# Detect all conflict types: value, type, relationship, temporal, logical
detector = ConflictDetector()
conflicts = detector.detect_conflicts(entities_from_source_a + entities_from_source_b)
# → [Conflict(entity="alice_chen", field="role", values=["CTO","VP Eng"], severity="HIGH"),
# Conflict(entity="alice_chen", field="salary", values=[250000,275000], severity="MEDIUM")]
# Resolve using multiple strategies
resolver = ConflictResolver()
resolved = resolver.resolve(conflicts, strategy="credibility_weighted") # weighted by source trust
resolved = resolver.resolve(conflicts, strategy="temporal") # prefer most recent
resolved = resolver.resolve(conflicts, strategy="voting") # majority wins
# Track source credibility over time
tracker = SourceTracker()
tracker.track("source_a", credibility=0.85)
tracker.track("source_b", credibility=0.72)
```
---
### `semantica.deduplication`: Entity Resolution at Scale
Block, cluster, and merge duplicates with semantic similarity. **6.98× faster** than baseline.
```python
from semantica.deduplication import DuplicateDetector, EntityMerger
entities = [
{"id": "e1", "name": "Acme Corporation", "domain": "acme.com"},
{"id": "e2", "name": "Acme Corp.", "domain": "acme.com"},
{"id": "e3", "name": "ACME Corp", "domain": "acme.co"},
{"id": "e4", "name": "Globex Industries", "domain": "globex.com"},
]
detector = DuplicateDetector(similarity_threshold=0.75, use_clustering=True)
candidates = detector.detect_duplicates(entities)
groups = detector.detect_duplicate_groups(entities)
# → DuplicateGroup(entities=["e1","e2","e3"], confidence=0.91, strategy="semantic+blocking")
merger = EntityMerger(preserve_provenance=True)
ops = merger.merge_duplicates(entities, strategy="keep_most_complete")
history = merger.get_merge_history()
```
---
### `semantica.normalize`: Data Normalization & Cleaning
Standardize text, entities, dates, numbers, and encodings before building your knowledge graph.
```python
from semantica.normalize import (
TextNormalizer,
EntityNormalizer,
DateNormalizer,
NumberNormalizer,
DataCleaner,
)
# Unicode, whitespace, casing, HTML tags, smart quotes
text = TextNormalizer().normalize(" Acme Corp.’s Q4 report… ")
# → "Acme Corp.'s Q4 report..."
# Alias resolution + entity disambiguation with confidence scores
names = EntityNormalizer().normalize_entity("ACME Corp.")
# → NormalizedEntity(canonical="Acme Corporation", type="Organization", confidence=0.91)
# Natural language date parsing with timezone conversion
dt = DateNormalizer().normalize_date("3 weeks ago")
# → datetime(2026, 5, 22, tzinfo=UTC)
# Unit conversion and currency normalization
price = NumberNormalizer().normalize("$1.25M USD")
# → NormalizedNumber(value=1_250_000, currency="USD")
# Deduplicate and impute missing values across a dataset
clean = DataCleaner().clean(records, dedup_threshold=0.9, fill_missing="mean")
```
---
### `semantica.pipeline`: Pipeline DSL
Compose ingestion, extraction, and graph-building into a declarative, parallel pipeline.
```python
from semantica.pipeline import PipelineBuilder, ExecutionEngine
pipeline = (
PipelineBuilder()
.add_step("ingest", step_type="ingest", source="./contracts/", recursive=True)
.add_step("extract", step_type="ner_extract")
.add_step("relations", step_type="relation_extract")
.add_step("build_kg", step_type="kg_build", merge_entities=True)
.add_step("deduplicate", step_type="deduplicate", threshold=0.75)
.add_step("export", step_type="export", format="turtle", output="kg.ttl")
.connect_steps("ingest", "extract")
.connect_steps("extract", "relations")
.connect_steps("relations", "build_kg")
.connect_steps("build_kg", "deduplicate")
.connect_steps("deduplicate", "export")
.set_parallelism(4)
.build(name="contracts_pipeline")
)
engine = ExecutionEngine()
result = engine.execute(pipeline)
status = engine.get_status(pipeline)
progress = engine.get_progress(pipeline)
```
---
### Temporal Intelligence: Bi-Temporal Graphs & Time Travel
Track when facts were true *in the world* vs. when they were *recorded*, and query either axis.
```python
from semantica.context import ContextGraph
from semantica.kg import (
BiTemporalFact,
TemporalGraphQuery,
TemporalVersionManager,
TemporalNormalizer,
)
from datetime import datetime
graph = ContextGraph(advanced_analytics=True)
graph.add_node("alice_chen", "Person", role="VP Engineering")
graph.add_node("acme_corp", "Organization", valuation=1_200_000_000)
# Point-in-time snapshots - replay history without reprocessing
snapshot_2023 = graph.state_at("2023-06-01")
snapshot_2024 = graph.state_at("2024-01-01")
# Bi-temporal facts - valid_time is when true in the world;
# recorded_at is when you learned about it
fact = BiTemporalFact(
valid_from=datetime(2024, 3, 1),
valid_until=datetime(2025, 1, 1),
recorded_at=datetime(2024, 3, 5),
)
# Allen interval algebra - 13 temporal relations (before, during, overlaps, etc.)
tq = TemporalGraphQuery(graph)
facts_in_window = tq.query_time_range("2024-01-01", "2024-12-31")
# Normalize natural language temporal expressions
norm = TemporalNormalizer()
dt = norm.normalize("last quarter") # → datetime range for Q1 2026
```
---
### `semantica.export`: RDF, OWL, Parquet, Cypher, JSON-LD
Export to any format required by regulators, graph databases, or downstream systems.
```python
from semantica.export import (
RDFExporter,
JSONExporter,
ParquetExporter,
LPGExporter,
ReportGenerator,
)
kg = {"entities": [...], "relationships": [...]}
rdf = RDFExporter()
turtle_str = rdf.export_to_rdf(kg, format="turtle") # returns string
jsonld_str = rdf.export_to_rdf(kg, format="json-ld")
rdf.export(kg, "kg_audit.ttl", format="turtle")
rdf.export(kg, "kg_audit.jsonld", format="json-ld")
rdf.export(kg, "kg_audit.nt", format="n-triples")
# Columnar analytics - Snappy-compressed Parquet
ParquetExporter().export(kg, "kg_snapshot.parquet", compression="snappy")
# JSON knowledge graph
JSONExporter().export_knowledge_graph(kg, "kg.json")
# Neo4j / Memgraph Cypher statements for graph database import
LPGExporter().export(kg, "kg_import.cypher", method="cypher")
# Human-readable HTML / Markdown report
ReportGenerator().generate(kg, "audit_report.html", format="html")
```
---
### `semantica.visualization`: Interactive Graph Workbench
Render force-directed graphs, community maps, ontology hierarchies, and temporal dashboards.
```python
from semantica.visualization import (
KGVisualizer,
OntologyVisualizer,
EmbeddingVisualizer,
TemporalVisualizer,
)
import numpy as np
kg = {"entities": [...], "relationships": [...]}
# Interactive force-directed graph (opens in browser)
viz = KGVisualizer(layout="force", color_scheme="default")
viz.visualize_network(kg, output="interactive", file_path="kg.html")
viz.visualize_communities(kg, communities, output="interactive")
viz.visualize_centrality(kg, centrality, centrality_type="degree")
viz.visualize_entity_types(kg, output="html", file_path="entity_types.html")
# Ontology class hierarchy
OntologyVisualizer().visualize_hierarchy(ontology, output="interactive")
# 2D embedding projection (UMAP / t-SNE / PCA)
EmbeddingVisualizer().visualize_2d_projection(
embeddings=np.array([...]),
labels=["entity_a", "entity_b"],
method="umap",
)
# Timeline scrubber - watch the graph evolve
TemporalVisualizer().visualize_timeline(kg, output="interactive")
```
---
### Multi-Agent Shared Context with Agno
One shared intelligence layer. All agents read and write to the same context graph.
```python
# pip install semantica[agno]
from agno.agent import Agent
from agno.team import Team
from agno.models.anthropic import Claude
from semantica.context import ContextGraph
from semantica.vector_store import VectorStore
from integrations.agno import AgnoSharedContext, AgnoDecisionKit, AgnoKGToolkit
shared = AgnoSharedContext(
vector_store=VectorStore(backend="faiss"),
knowledge_graph=ContextGraph(advanced_analytics=True),
decision_tracking=True,
)
researcher = Agent(
name="Researcher",
model=Claude(id="claude-sonnet-4-6"),
memory=shared.bind_agent("researcher"),
tools=[AgnoKGToolkit(context=shared)],
)
analyst = Agent(
name="Analyst",
model=Claude(id="claude-sonnet-4-6"),
memory=shared.bind_agent("analyst"),
tools=[AgnoDecisionKit(context=shared)],
)
team = Team(agents=[researcher, analyst], mode="coordinate")
# Researcher's findings are instantly available to the Analyst - no copy, no sync
```
→ [runnable notebooks in the cookbook](https://github.com/semantica-agi/semantica/tree/main/cookbook), each self-contained and runnable in under 5 minutes
---
## Recipes
Copy-paste patterns for the most common use cases.
### End-to-End GraphRAG Pipeline
```python
from semantica.ingest import FileIngestor
from semantica.split import TextSplitter
from semantica.semantic_extract import NamedEntityRecognizer, RelationExtractor
from semantica.kg import GraphBuilder
from semantica.vector_store import VectorStore, HybridSearch
from semantica.context import AgentContext
# 1. Ingest
docs = FileIngestor().ingest_directory("./docs/", recursive=True)
# 2. Entity-aware chunking - never splits an entity across a chunk boundary
splitter = TextSplitter(method="entity_aware", chunk_size=1000)
chunks = [splitter.split(doc["text"]) for doc in docs]
# 3. Extract entities and relations
ner = NamedEntityRecognizer(confidence_threshold=0.7)
rel_ext = RelationExtractor(confidence_threshold=0.6)
entities = [ner.extract_entities(chunk) for chunk_group in chunks for chunk in chunk_group]
# 4. Build KG
kg = GraphBuilder(merge_entities=True, enable_temporal=True).build(docs)
# 5. Hybrid retrieval
vs = VectorStore(backend="faiss")
ctx = AgentContext(vector_store=vs, knowledge_graph=kg)
ctx.store("Alice approved the Acme renewal in Q1 2024", conversation_id="c1")
results = HybridSearch(vector_store=vs).search("who approved the renewal?")
```
---
### Audit Trail for a Regulated Decision
```python
from semantica.context import ContextGraph
from semantica.provenance import ProvenanceManager
from semantica.export import RDFExporter
graph = ContextGraph(advanced_analytics=True)
prov = ProvenanceManager(storage_path="./audit.db")
# Record the decision chain
d1 = graph.record_decision(
category="loan_application", scenario="A-7291, $85k income",
reasoning="Income threshold met", outcome="proceed", confidence=0.88,
)
d2 = graph.record_decision(
category="loan_underwriting", scenario="Underwriting A-7291",
reasoning="Clean credit history", outcome="approved", confidence=0.94,
)
graph.add_causal_relationship(d1, d2, relationship_type="triggers")
# Track provenance for every entity
prov.track_entity("applicant_A7291", source="loan_application_form.pdf",
metadata={"page": 1, "extractor": "NamedEntityRecognizer"})
# Export W3C PROV-O for regulator submission
kg = graph.export_graph()
RDFExporter().export(kg, "audit_trail.ttl", format="turtle")
```
---
### AML Rules Engine
```python
from semantica.reasoning import ReteEngine, Rule, Fact, RuleType
rete = ReteEngine()
rete.build_network([
Rule(
rule_id="sanctions_check",
name="Flag sanctioned-country transactions",
conditions=[
{"field": "amount", "operator": ">", "value": 10_000},
{"field": "country", "operator": "in", "value": ["IR", "KP", "SY", "CU"]},
],
conclusion="flag_for_compliance_review",
rule_type=RuleType.IMPLICATION,
),
])
rete.add_fact(Fact("tx_99", "transaction", [{"amount": 25_000, "country": "IR"}]))
matches = rete.match_patterns()
# → [{"rule": "sanctions_check", "matched_facts": ["tx_99"],
# "conclusion": "flag_for_compliance_review"}]
```
---
### Ontology-to-Knowledge-Graph in One Pass
```python
from semantica.ingest import FileIngestor
from semantica.semantic_extract import NamedEntityRecognizer, RelationExtractor
from semantica.kg import GraphBuilder
from semantica.ontology import OntologyGenerator, OntologyValidator
from semantica.export import RDFExporter
sources = FileIngestor().ingest_directory("./contracts/")
ner = NamedEntityRecognizer(confidence_threshold=0.7)
entities = ner.extract_entities_batch([s["text"] for s in sources])
kg = GraphBuilder(merge_entities=True).build(sources)
gen = OntologyGenerator(base_uri="https://myco.dev/ontology/")
ont = gen.generate_ontology({"entities": entities[0], "relationships": []})
report = OntologyValidator().validate(ont)
if report.conforms:
RDFExporter().export({"entities": entities[0]}, "ontology.ttl", format="turtle")
```
---
## Performance
Benchmarks from v0.5.0 on a 118,000-node production graph:
| Operation | Before | After | Improvement |
| --- | --- | --- | --- |
| Node search (118k nodes) | 24 ms | 0.004 ms | **6,000×** faster |
| Embedding cache hit | cold load | revision-based cache | **10×** throughput |
| Semantic deduplication | baseline | optimized candidate gen | **6.98×** faster |
| Candidate generation | baseline | blocking strategy | **63.6%** faster |
*Measured on a 118,000-node production graph (AMD EPYC, 64 GB RAM). Results vary by hardware, dataset topology, and backend selection. Run `pytest tests/vector_store/test_performance_benchmarks.py -s` to measure your own data.*
---
## CLI
Every capability is available from the terminal. The CLI ships with the package, no separate install required.
```bash
pip install semantica
semantica # startup dashboard
semantica doctor # health check
semantica --help # full grouped command reference
```
Start with `semantica`, verify with `doctor`, build a graph, and explore the command groups from one terminal.
**Command groups:** `ingest` · `parse` · `extract` · `kg` · `reason` · `decision` · `temporal` · `provenance` · `ontology` · `embed` · `deduplicate` · `validate` · `export` · `visualize` · `pipeline` · `server` · `explorer` · `mcp` · `doctor` · `shell` · `init` · `watch`
→ [Full CLI reference](https://docs.getsemantica.ai/)
---
## Integrations
Native plugin bundles across major editors, a full-featured MCP server, a comprehensive REST API, and first-class Agno support. All LLM providers already supported: OpenAI · Anthropic · Gemini · Mistral · Llama · Groq · Cohere · Azure · Bedrock · Ollama · DeepSeek · HuggingFace and more via LiteLLM
---
## Contributing
All contributions are welcome: bug fixes, features, tests, and documentation.
1. Fork the repo and create a branch
2. `pip install -e ".[dev]"`
3. Write tests alongside your changes (`pytest tests/`)
4. Open a PR and tag `@KaifAhmad1` for review
See [CONTRIBUTING.md](CONTRIBUTING.md) for full guidelines.
---
MIT License · Built by [Semantica](https://github.com/semantica-agi)
[GitHub](https://github.com/semantica-agi/semantica) ·
[Discord](https://discord.gg/sV34vps5hH) ·
[Twitter/X](https://x.com/BuildSemantica) ·
[Website](https://getsemantica.ai/) ·
[Docs](https://docs.getsemantica.ai/) ·
[PyPI](https://pypi.org/project/semantica/)
If this project helps you build better AI, a star means a lot.
**[⭐ Star on GitHub →](https://github.com/semantica-agi/semantica)**
[English](https://readme-i18n.com/semantica-agi/semantica?lang=en) · [Deutsch](https://readme-i18n.com/semantica-agi/semantica?lang=de) · [Français](https://readme-i18n.com/semantica-agi/semantica?lang=fr) · [Español](https://readme-i18n.com/semantica-agi/semantica?lang=es) · [Italiano](https://readme-i18n.com/semantica-agi/semantica?lang=it) · [Português](https://readme-i18n.com/semantica-agi/semantica?lang=pt) · [العربية](https://readme-i18n.com/semantica-agi/semantica?lang=ar) · [اردو](https://readme-i18n.com/semantica-agi/semantica?lang=ur) · [हिन्दी](https://readme-i18n.com/semantica-agi/semantica?lang=hi) · [中文](https://readme-i18n.com/semantica-agi/semantica?lang=zh) · [日本語](https://readme-i18n.com/semantica-agi/semantica?lang=ja) · [한국어](https://readme-i18n.com/semantica-agi/semantica?lang=ko)
### The Context and Accountability Layer for AI Agents
> Semantica is the Context and Accountability Layer for AI agents: context graphs, decision intelligence, explainable reasoning, and policy governance, with a permanent audit trail behind every decision.
>
> It's the intelligence category **Palantir** built for the enterprise, delivered **100% open source** and self-hostable, with zero black boxes and zero vendor lock-in, from startup to Fortune 500, without the seven-figure contract.
**Decision Intelligence · Context Management · Deterministic Reasoning · Traceability**
**Open Source · Auditable · Governed · Self-Hostable**
**Polyglot Graph Storage**
[](https://github.com/semantica-agi/semantica) [](https://pypi.org/project/semantica/) [](https://pepy.tech/project/semantica) [](https://www.python.org/) [](https://opensource.org/licenses/MIT) [](https://github.com/semantica-agi/semantica/actions) [](https://deepwiki.com/semantica-agi/semantica)
[](https://getsemantica.ai/) [](https://docs.getsemantica.ai/) [](https://discord.gg/sV34vps5hH) [](https://x.com/BuildSemantica) [](https://www.youtube.com/watch?v=QfnNZg4-dZA) [](CHANGELOG.md)
