Command
Search PubMed and download articles into a local corpus for epistract ingestion.
Epistract is a domain-agnostic knowledge graph framework that runs as a Claude Code plugin. Point it at a folder of documents, specify a domain schema, and it builds a two-layer knowledge graph: brute-force entity/relation extraction grounded to domain ontologies, then domain-specific epistemic analysis
Command
Search PubMed and download articles into a local corpus for epistract ingestion.
Command
Add source documents to an epistract project corpus (deduplicated by content hash).
Command
Fetch one or more URLs into an epistract project corpus (deduplicated by content hash).
Command
Ask questions about extracted contract knowledge graph — answers with citations, cost breakdowns, and risk analysis.
Command
Build knowledge graph from existing epistract extractions.
Command
Launch the interactive web workbench for exploring a knowledge graph — chat + force-directed graph + source inspector.
Command
Remove a domain — archive to a recoverable location or permanently delete — with explicit confirmation.
Command
List all installed domains — active and archived — with entity type count, relation type count, last-modified date, and status.
Command
Edit a domain component — schema, extraction prompt, or epistemic analysis — via a guided conversational wizard.
Command
Create a new domain package from sample documents using guided wizard.
Command
Run arXiv-backed quality passes over a project's knowledge graph — triple judging, entity resolution, and a bi-temporal epistemic layer.
Command
Analyze epistemic patterns (hypotheses, contradictions, conditional claims) in a built knowledge graph and produce a Super Domain claims layer.
Command
Export knowledge graph to GraphML, GEXF, CSV, SQLite, or JSON.
Command
Incrementally index an epistract project's corpus and graph for hybrid search.
Command
Ingest scientific documents and build a drug discovery knowledge graph.
Command
Create a new named epistract project (persistent dataset) with its own corpus, graph, and search index.
Command
List, inspect, or delete epistract projects in the registry.
Command
Search entities in the drug discovery knowledge graph.
Command
Hybrid search over an epistract project — entities and document chunks, with optional graph expansion.
Command
Install and verify epistract dependencies (sift-kg, optional RDKit/Biopython).
Command
Validate molecular identifiers (SMILES, sequences) in extraction results.
Command
Open interactive knowledge graph visualization in browser.