#1818th of 18 in Memory
semantica
Python library for building context graphs with decision provenance and reasoning
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 13.8k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Semantica is a Python library that ingests data from files, databases, Databricks, Snowflake and SAP, extracts entities and relations, and builds a knowledge graph with W3C PROV-O provenance. It records agent decisions as graph nodes with causal links, and runs rule-based reasoning (Rete, Datalog, SPARQL) and SHACL/OWL governance. It stores graphs in RDF or property-graph backends and exposes a CLI, REST API and MCP server.
Who it is for: Teams building auditable agent context and knowledge graphs in regulated domains
Strengths
- Graph construction, reasoning and provenance are deterministic; no LLM required
- Swappable storage: Oxigraph, Blazegraph, Jena, RDF4J, Neo4j, FalkorDB, AGE, Neptune
- Decisions stored as graph nodes with causal tracing, precedent search and PROV-O export
- Connectors for Databricks, Snowflake, SAP OData, Kafka, Kinesis, plus CrewAI, LangChain, Agno integrations
Weaknesses
- Broad scope (ontology, reasoning, ingestion, analytics) means a large surface to learn
- Explains context and decisions outside the LLM only, not the model's internal reasoning
- Resource requirements and benchmark figures not stated in the visible README
- Aimed at regulated enterprise use; heavy for simple agent memory needs
What it needs
- no GPU
- Docker + Compose
- Needs Optional graph stores: Neo4j, FalkorDB, Apache AGE, AWS Neptune, Blazegraph, Jena, RDF4J, Optional vector store: FAISS, Optional LLM provider: OpenAI, Anthropic, Gemini
- Models: OpenAI, Anthropic, Gemini
Also in Memory
See all 18| Rank | Project | Score |
|---|---|---|
| 1 | gbrainLong-term memory store for coding agents, with sources and corrections | 85 out of 100 |
| 2 | hindsightAgent memory server with retain, recall and reflect operations | 80 out of 100 |
| 3 | CogneeMemory engine that turns documents and code into a knowledge graph | 79 out of 100 |
| #4 | MemPalaceLocal long-term memory store for agents with verbatim storage and semantic search | 78 out of 100 |
| #5 | agentmemoryPersistent cross-session memory for coding agents via hooks, MCP and REST | 77 out of 100 |