# Semantica

> Operate semantica-agi/semantica, the Python graph-native knowledge engineering toolkit: choose ingestion, parsing, extraction, graph/triplet/vector stores, CLI, server or MCP entrypoints; diagnose optional integrations and backend configuration. Use when users name Semantica or ask for a modular Python pipeline spanning documents, knowledge graphs, provenance or reasoning. It is an application/library framework, not a single graph database; route a dedicated ontology workbench to OrionBelt or certified ontology change planning to Open Ontologies.

- Skill: `akillness/semantica` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx get-skill add akillness/semantica`
- Raw SKILL.md: https://api.skillmd.com/api/skills/akillness/semantica/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: akillness (https://skillmd.com/u/akillness)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/akillness/semantica

---


# Semantica

## Instructions

1. Select the task layer first: package API, `semantica` CLI, standalone server/worker/explorer, MCP, or a specific optional connector. Confirm the exact extra and backend from the pinned `pyproject.toml` before proposing installs.
2. Treat commands and data flow as scoped examples; inspect installed CLI help/source for exact syntax. Build a minimal environment and add only the extra required. Avoid `[all]` unless user explicitly requests the broad dependency set and accepts its footprint.
3. Before configuring a model/provider, database, cloud service, or MCP client, obtain explicit approval for credential use, external calls, uploads, cost, data access, and configuration changes. Never ask for or print secret values; prefer documented environment/config references and local endpoints where appropriate.
4. Distinguish package graph-store backends (e.g. Neo4j/FalkorDB/Neptune/AGE) from the overall toolkit. Explain connector prerequisites and distinguish offline code inspection from runtime, service, or provider verification.

## Examples

- “Which Semantica extras do I need to ingest documents and store triples in Oxigraph?”
- “Trace this Semantica CLI/MCP startup failure without using credentials.”
- “Plan a minimal local pipeline for parsing and entity extraction.”

## Best practices

- The pinned CLI is a Click-based command surface; use `semantica --help` or its own subcommand help rather than guessing flags.
- `python -m semantica.mcp_server` delegates to the MCP server entrypoint, but that alone does not establish a client configuration or active server.
- Read [`references/upstream.md`](references/upstream.md) before backend/provider advice; source metadata does not prove a dependency is installed or service is healthy.

## References

- [`references/upstream.md`](references/upstream.md) - supported setup/runtime entrypoints, extras, limits, licensing and safety.
- [`references/source.json`](references/source.json) - selected pinned file SHA256s; not a whole-revision attestation.
- [`evals/evals.json`](evals/evals.json) - authored routing and boundary scenarios, not executed model-quality tests.

