@@ -122,8 +122,8 @@ If Semantica solves a real problem for you, a star helps others find it.
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
+- [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)**
@@ -146,10 +146,32 @@ Every component is independently importable. Use one module or all of them.
| **Entity resolution** | No | No | Blocking + semantic deduplication |
| **Multi-agent context** | Separate per agent | Separate per agent | Single shared intelligence layer |
-Semantica does not replace your LLM or your vector store — it adds the structured intelligence and accountability layer they cannot provide.
+> [!IMPORTANT]
+> **Semantica complements your existing stack — it does not replace anything you already have.** 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. Your stack handles retrieval and generation. Semantica handles accountability and explainability. They are built to work together.
> [!NOTE]
-> Semantica is designed for AI agents, GraphRAG systems, enterprise knowledge intelligence, and temporal reasoning applications. The reasoning engines, KG construction, and provenance layer are fully deterministic — no LLM is required to use them.
+> Semantica is designed for AI agents, GraphRAG systems, enterprise knowledge intelligence, and temporal reasoning applications. The reasoning engines, KG construction, and provenance layer are fully deterministic; no LLM is required to use them.
+
+### How Semantica Compares
+
+Most AI frameworks are built for retrieval. Semantica is built for accountability. The comparison below focuses on the intelligence capabilities that define the difference.
+
+| | LangChain | LlamaIndex | MS GraphRAG | Mem0 | Zep | **Semantica** |
+| --- | :---: | :---: | :---: | :---: | :---: | :---: |
+| **Knowledge Graph construction** | ⚡ Plugin | ⚡ PropertyGraph | ⚡ Community KG | ❌ | ❌ | ✅ Native, full-stack |
+| **Decision tracking** | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ First-class objects |
+| **Audit trail & provenance** | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ W3C PROV-O, exportable |
+| **Explainable reasoning** | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ Rete · Datalog · SPARQL |
+| **Ontology (OWL / SHACL)** | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ Generation + visual editor |
+| **Conflict detection** | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ 5 resolution strategies |
+| **Bi-temporal graph & time travel** | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ Point-in-time snapshots |
+| **Entity resolution** | ❌ | ⚡ Partial | ⚡ Partial | ❌ | ⚡ Partial | ✅ Blocking + semantic dedup |
+| **Multi-agent shared context** | ⚡ LangGraph | ⚡ Partial | ❌ | ✅ | ⚡ Partial | ✅ Single shared graph |
+| **Policy enforcement** | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ SHACL + rule engine |
+
+> ✅ Full support ⚡ Partial / via plugin ❌ Not supported
+
+**The key distinction:** LangChain, LlamaIndex, and MS GraphRAG are excellent retrieval and orchestration layers. Mem0 and Zep excel at personal agent memory. None of them answer *"prove what your AI decided, why, and whether it complied with policy."* Semantica is built specifically for that question.
---
@@ -157,7 +179,7 @@ Semantica does not replace your LLM or your vector store — it adds the structu
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.
+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
@@ -174,13 +196,13 @@ graph.add_node("contract_001", "Contract", value=2_400_000, currency="USD")
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
+# 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
+# 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
+# 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")
@@ -189,8 +211,8 @@ retrieved = ctx.retrieve("who approved the Acme contract?")
**Why graph over embeddings:**
-- Traversal finds connections embeddings miss — a person 3 hops from a contract
-- Every node carries provenance — you can always ask *"where did this come from?"*
+- 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
@@ -198,19 +220,19 @@ retrieved = ctx.retrieve("who approved the Acme contract?")
## 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 ask with increasing frequency.
+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:
> [!IMPORTANT]
-> In regulated domains (healthcare, finance, legal, government), 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.
+> In regulated domains (healthcare, finance, legal, government), 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
+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
```
@@ -223,7 +245,7 @@ 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",
+ 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,
@@ -262,9 +284,9 @@ insights = graph.get_decision_insights()
Semantica is a full platform. Every module is independently importable and composable. Below are working examples for each.
-### `semantica.ingest` — Multi-Source Ingestion
+### `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.
+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
@@ -278,7 +300,7 @@ 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
+# 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"],
@@ -290,7 +312,7 @@ rows = DBIngestor().ingest_database(
---
-### `semantica.semantic_extract` — NER, Relations, Events, Triplets
+### `semantica.semantic_extract`: NER, Relations, Events, Triplets
Extract structured knowledge from raw text in one pass.
@@ -313,7 +335,7 @@ 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
+# 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"),
@@ -331,7 +353,7 @@ triplets = TripletExtractor(include_temporal=True, include_provenance=True).extr
---
-### `semantica.kg` — Knowledge Graph Construction & Analysis
+### `semantica.kg`: Knowledge Graph Construction & Analysis
Build a production knowledge graph from documents and run graph algorithms over it.
@@ -348,7 +370,7 @@ from semantica.kg import (
)
from datetime import datetime
-# Build KG — merge duplicate entities, track temporal edges
+# 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)
@@ -364,7 +386,7 @@ communities = CommunityDetector().detect_communities(kg, method="louvain") # na
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
+# Bi-temporal facts - track valid time vs. recorded time independently
fact = BiTemporalFact(
valid_from=datetime(2024, 3, 1),
valid_until=datetime(2025, 1, 1),
@@ -374,9 +396,9 @@ fact = BiTemporalFact(
---
-### `semantica.reasoning` — Forward Chaining, Rete, Datalog, SPARQL
+### `semantica.reasoning`: Forward Chaining, Rete, Datalog, SPARQL
-Run explainable rule-based inference — not a black box.
+Run explainable rule-based inference, not a black box.
```python
from semantica.reasoning import ReteEngine, Rule, Fact, RuleType
@@ -411,7 +433,7 @@ flagged = rete.match_patterns()
```
```python
-# Recursive Datalog — natural language for graph queries
+# Recursive Datalog - natural language for graph queries
from semantica.reasoning import DatalogReasoner
engine = DatalogReasoner()
@@ -425,7 +447,7 @@ ancestors = engine.query("ancestor(tom, ?X)")
```
```python
-# Explainable reasoning — trace the path, not just the answer
+# Explainable reasoning - trace the path, not just the answer
from semantica.reasoning import ExplanationGenerator, Reasoner
reasoner = Reasoner()
@@ -438,7 +460,7 @@ explanation = explainer.generate(result)
---
-### `semantica.vector_store` — Hybrid & Filtered Semantic Search
+### `semantica.vector_store`: Hybrid & Filtered Semantic Search
Drop-in vector store with 7 backends, hybrid search, and decision-aware retrieval.
@@ -450,7 +472,7 @@ 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",
+ scenario="Personal loan A-7291, $85k income, 31% DTI, 3yr employment",
outcome="approved",
confidence=0.94,
category="loan_underwriting",
@@ -462,7 +484,7 @@ results = vs.search(
limit=10,
)
-# Hybrid search — dense + sparse retrieval in one pass with RRF fusion
+# Hybrid search - dense + sparse retrieval in one pass with RRF fusion
hs = HybridSearch(vector_store=vs)
hits = hs.search("high-risk transactions 2024")
@@ -475,9 +497,9 @@ explanation = vs.explain_decision(results[0]["id"])
> [!CAUTION]
> Mixing vectors generated from different embedding models in the same `VectorStore` index leads to inconsistent similarity scores. Always use a single embedding model per index, or isolate per-model data using namespaces.
-### `semantica.split` — GraphRAG-Native Document Chunking
+### `semantica.split`: GraphRAG-Native Document Chunking
-KG-aware splitting that preserves entity boundaries, relation triplets, and ontology concepts — essential for GraphRAG pipelines.
+KG-aware splitting that preserves entity boundaries, relation triplets, and ontology concepts, essential for GraphRAG pipelines.
```python
from semantica.split import TextSplitter, EntityAwareChunker, RelationAwareChunker
@@ -487,16 +509,16 @@ 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)
+# 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
+# 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
+# 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)
+# Hierarchical chunking - multi-level (section → paragraph → sentence)
chunks = TextSplitter(method="hierarchical", levels=["section", "paragraph"]).split(text)
```
@@ -504,9 +526,9 @@ chunks = TextSplitter(method="hierarchical", levels=["section", "paragraph"]).sp
---
-### `semantica.provenance` — W3C PROV-O Lineage
+### `semantica.provenance`: W3C PROV-O Lineage
-Every fact linked to its source — no black boxes, no mystery outputs.
+Every fact is linked to its source. No black boxes, no mystery outputs.
```python
from semantica.provenance import ProvenanceManager
@@ -535,7 +557,7 @@ entry = prov.get_provenance("acme_corp")
---
-### `semantica.ontology` — OWL Generation, SHACL Validation
+### `semantica.ontology`: OWL Generation, SHACL Validation
Generate ontologies from data, validate shapes, and manage your vocabulary.
@@ -566,7 +588,7 @@ report = validator.validate(ontology)
---
-### `semantica.conflicts` — Conflict Detection & Resolution
+### `semantica.conflicts`: Conflict Detection & Resolution
Detect and resolve conflicting facts from multiple sources before they corrupt your knowledge base.
@@ -600,9 +622,9 @@ tracker.track("source_b", credibility=0.72)
---
-### `semantica.deduplication` — Entity Resolution at Scale
+### `semantica.deduplication`: Entity Resolution at Scale
-Block, cluster, and merge duplicates with semantic similarity — **6.98× faster** than baseline.
+Block, cluster, and merge duplicates with semantic similarity. **6.98× faster** than baseline.
```python
from semantica.deduplication import DuplicateDetector, EntityMerger
@@ -626,7 +648,7 @@ history = merger.get_merge_history()
---
-### `semantica.normalize` — Data Normalization & Cleaning
+### `semantica.normalize`: Data Normalization & Cleaning
Standardize text, entities, dates, numbers, and encodings before building your knowledge graph.
@@ -661,7 +683,7 @@ clean = DataCleaner().clean(records, dedup_threshold=0.9, fill_missing="mean")
---
-### `semantica.pipeline` — Pipeline DSL
+### `semantica.pipeline`: Pipeline DSL
Compose ingestion, extraction, and graph-building into a declarative, parallel pipeline.
@@ -696,9 +718,9 @@ progress = engine.get_progress(pipeline)
---
-### Temporal Intelligence — Bi-Temporal Graphs & Time Travel
+### Temporal Intelligence: Bi-Temporal Graphs & Time Travel
-Track when facts were true *in the world* vs. when they were *recorded* — and query either axis.
+Track when facts were true *in the world* vs. when they were *recorded*, and query either axis.
```python
from semantica.context import ContextGraph
@@ -714,11 +736,11 @@ 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
+# 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;
+# 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),
@@ -726,7 +748,7 @@ fact = BiTemporalFact(
recorded_at=datetime(2024, 3, 5),
)
-# Allen interval algebra — 13 temporal relations (before, during, overlaps, etc.)
+# 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")
@@ -737,7 +759,7 @@ dt = norm.normalize("last quarter") # → datetime range for Q1 2026
---
-### `semantica.export` — RDF, OWL, Parquet, Cypher, JSON-LD
+### `semantica.export`: RDF, OWL, Parquet, Cypher, JSON-LD
Export to any format required by regulators, graph databases, or downstream systems.
@@ -760,7 +782,7 @@ 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
+# Columnar analytics - Snappy-compressed Parquet
ParquetExporter().export(kg, "kg_snapshot.parquet", compression="snappy")
# JSON knowledge graph
@@ -775,7 +797,7 @@ ReportGenerator().generate(kg, "audit_report.html", format="html")
---
-### `semantica.visualization` — Interactive Graph Workbench
+### `semantica.visualization`: Interactive Graph Workbench
Render force-directed graphs, community maps, ontology hierarchies, and temporal dashboards.
@@ -807,7 +829,7 @@ EmbeddingVisualizer().visualize_2d_projection(
method="umap",
)
-# Timeline scrubber — watch the graph evolve
+# Timeline scrubber - watch the graph evolve
TemporalVisualizer().visualize_timeline(kg, output="interactive")
```
@@ -815,7 +837,7 @@ 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.
+One shared intelligence layer. All agents read and write to the same context graph.
```python
# pip install semantica[agno]
@@ -846,13 +868,13 @@ analyst = Agent(
)
team = Team(agents=[researcher, analyst], mode="coordinate")
-# Researcher's findings are instantly available to the Analyst — no copy, no sync
+# Researcher's findings are instantly available to the Analyst - no copy, no sync
```
→ [40+ runnable notebooks in the cookbook](https://github.com/semantica-agi/semantica/tree/main/cookbook)
> [!TIP]
-> New to Semantica? Start with the [cookbook notebooks](https://github.com/semantica-agi/semantica/tree/main/cookbook) — they walk through each module end-to-end with real datasets before you write production code. Each notebook is self-contained and runnable in under 5 minutes.
+> New to Semantica? Start with the [cookbook notebooks](https://github.com/semantica-agi/semantica/tree/main/cookbook). They walk through each module end-to-end with real datasets before you write production code. Each notebook is self-contained and runnable in under 5 minutes.
---
@@ -873,7 +895,7 @@ 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
+# 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]
@@ -907,7 +929,7 @@ prov = ProvenanceManager(storage_path="./audit.db")
# Record the decision chain
d1 = graph.record_decision(
- category="loan_application", scenario="A-7291 — $85k income",
+ category="loan_application", scenario="A-7291, $85k income",
reasoning="Income threshold met", outcome="proceed", confidence=0.88,
)
d2 = graph.record_decision(
@@ -995,7 +1017,7 @@ Benchmarks from v0.5.0 on a 118,000-node production graph:
## CLI
-Every capability is available from the terminal. The CLI ships with the package — no separate install.
+Every capability is available from the terminal. The CLI ships with the package, no separate install required.
```bash
pip install semantica
@@ -1043,7 +1065,7 @@ $ semantica kg build -s ./contracts/ -s ./reports/ --store neo4j
Knowledge graph built 1,847 nodes 4,203 edges 7.1s
```
-### `semantica doctor` — Health Check
+### `semantica doctor`: Health Check
```
$ semantica doctor
@@ -1064,7 +1086,7 @@ $ semantica doctor
## Integrations
-Native plugin bundles for 8 editors · MCP server with 12 tools · 109-endpoint REST API · Agno first-class · 100+ LLMs via LiteLLM
+Native plugin bundles for 8 editors · MCP server with 12 tools · 109-endpoint REST API · Agno first-class · All LLM providers already supported: OpenAI · Anthropic · Gemini · Mistral · Llama · Groq · Cohere · Azure · Bedrock · Ollama · DeepSeek · HuggingFace and more via LiteLLM
| Supported | +Native Integration | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| @@ -1175,43 +1197,78 @@ Native plugin bundles for 8 editors · MCP server with 12 tools · 109-endpoint | |||||||||||||||
| Coming Soon | +Already Supported via REST API & MCP | ||||||||||||||
 LangChain -Coming soon +REST API · MCP |
LangGraph -Coming soon +REST API · MCP |
 CrewAI -Coming soon +REST API · MCP |
 LlamaIndex -Coming soon +REST API · MCP |
 AutoGen -Coming soon +REST API · MCP |
 OpenAI Agents -Coming soon +REST API · MCP |
 Google ADK -Coming soon +REST API · MCP + |
+|||||||||
| Native SDK Integration — Coming Soon | +|||||||||||||||
|
+ +LangChain +Dedicated toolkit + |
+
+ +CrewAI +Dedicated toolkit + |
+
+ +LlamaIndex +Dedicated toolkit + |
+
+ +AutoGen +Dedicated toolkit + |
+
+ +OpenAI Agents +Dedicated toolkit + |
+
+ +Google ADK +Dedicated toolkit |
||||||||||