Hyper-Extract vs ontocast
Knowledge-extraction CLI: LLMs turn documents into structured graphs, hypergraphs and spatio-temporal knowledge — with an MCP server for agents and Obsidian vault export. — versus — Agentic ontology-assisted RDF extraction: co-evolves domain ontologies and fact graphs in a map/reduce pipeline with RDF 1.2 provenance, entity disambiguation and SHACL autofix.
Both turn documents into knowledge graphs with an LLM. hyper-extract goes wide — hypergraphs, spatio-temporal knowledge, MCP, Obsidian export; OntoCast goes deep on correctness: ontology co-evolution, provenance, disambiguation and SHACL validation.
| Hyper-Extract | ontocast | |
|---|---|---|
| Stars | 3.3k | 228 |
| Forks | 396 | 27 |
| Language | Python | Python |
| License | NOASSERTION | Apache-2.0 |
| Last activity | 12 days ago | 14 days ago |
| Topics | knowledge-graphs, rag | knowledge-graphs |
| Curated connections | 8 | 4 |
Hyper-Extract — the curator's take
The pitch beyond ordinary KG extraction is the hypergraph: relations that connect MORE than two entities survive instead of being flattened into pairwise triples. One command per document, query the abstracts over MCP from Claude Desktop or your IDE, export to Obsidian wikilinks. NOT a graph database (it extracts, storage stays simple) and no standard license resolution at review time — verify before building on it; extraction quality tracks the LLM you plug in.
ontocast — the curator's take
The extractor to pick when ontology drift is the thing that has burned you: schema and instances evolve in one loop, GraphUpdate insert/delete patches replace whole-graph regeneration, and SHACL validation repairs machine-fixable violations without another LLM pass. Runs as a REST service, a batch CLI, or a LangGraph node, with pyoxigraph in memory by default and Fuseki when you need persistence. Realities: it's research-grade (Zenodo DOI, 228 stars) with a configuration surface to match — 202 environment variables, and the docs sensibly ship a 47-variable minimal file plus playbooks. The LLM critic is off at the default `MAX_VISITS_PER_NODE=1`, so quality out of the box is one render pass.