ctakes
reference corpus · status live · domain HEALTH (Health and clinical reference) · lane A · refresh pinned · tags GLOBAL · CLINICAL-NLP · CONCEPT-EXTRACTION · UIMA · NEGATION
What an agent uses it for
An agent extracting concepts from clinical notes queries this for Apache cTAKES pipelines: section detection, negation/context, and UMLS dictionary lookup.
curl -fsSLO https://raw.githubusercontent.com/xerj-org/xerj/corpus-hub/tools/xerj-code/hub/ctakes.jsonxerj corpus add --from ./ctakes.jsonxerj corpus index ctakes then xerj code ctakes "your question"Needs the xerj CLI and a local node running; the copy prompt covers both, checks each step, and shows how to stop only the node you started. No shell: the MCP tool xerj_code_search with corpus: "ctakes", once the corpus is indexed on the node.
Sources and pins
| source | pin | licence | size | review note |
|---|---|---|---|---|
| ctakes | 80e0d8e951f8 | Apache-2.0 | 43.2 MB / 3,217 files | licence host-verified (ok-spdx): Apache-2.0 |
43.2 MB across 3,217 files. Added 2026-10-13.
Rights
Apache-2.0. Redistribution permitted with attribution per the licence review. The review block records a human opening each licence file at the pin. Detector output is a hint, never the verdict.
Retrieval spot-check (G7)
Not yet spot-checked. Queries are pre-registered in the registry before grading.