usathyan/epistract

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

8Stars on the repository

33Mods indexed here, across every type

17d agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 3 mods

acquirer

usathyan/epistract

Agent

Fetch a batch of PubMed articles for the epistract corpus. Dispatched by /epistract-acquire when processing many articles in parallel. Each agent handles a batch of PMIDs independently.

8 17d ago A 40 tokens original MIT

extractor

usathyan/epistract

Agent

Extract entities and relations from a single document for the epistract knowledge graph. Dispatched by /epistract-ingest when processing multiple documents in parallel. Each agent handles one document independently. Domain-aware: reads the domain SKILL.md for entity types, relation types, and naming standards.

8 17d ago A 59 tokens original MIT

validator

usathyan/epistract

Agent

Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.

8 17d ago A 53 tokens original MIT