diff --git a/nlp-service/CLAUDE.md b/nlp-service/CLAUDE.md
new file mode 100644
index 00000000..4b5300ea
--- /dev/null
+++ b/nlp-service/CLAUDE.md
@@ -0,0 +1,41 @@
+# NLP Service
+
+Lightweight FastAPI service that parses free-text search queries into structured extractions,
+replacing Ollama for the Familienarchiv NL search feature.
+
+## Stack
+
+- Python 3.11, FastAPI 0.115, spaCy 3.8, dateparser 1.2
+
+## Endpoints
+
+- `POST /parse` — parse a free-text query, return extraction matching `OllamaExtraction` contract
+- `GET /health` — returns `{"status": "ok"}` when all models are loaded
+
+## Running locally
+
+```bash
+pip install -r requirements.txt
+python -m spacy download de_core_news_sm en_core_web_sm es_core_news_sm
+uvicorn main:app --reload --port 8001
+
+curl -X POST http://localhost:8001/parse \
+  -H "Content-Type: application/json" \
+  -d '{"query": "Briefe von Opa Hermann an Marie vor 1920", "lang": "de"}'
+```
+
+## Testing
+
+```bash
+pytest -v
+```
+
+## Design spec
+
+See `docs/superpowers/specs/2026-06-07-spacy-nlp-service-design.md`.
+
+## Notes
+
+This is a **prototype** for extraction quality evaluation. No docker-compose integration or
+Java-side changes in this iteration. The extraction contract matches `OllamaExtraction` in
+`backend/src/main/java/org/raddatz/familienarchiv/search/`.
diff --git a/nlp-service/models.py b/nlp-service/models.py
new file mode 100644
index 00000000..e36fb89e
--- /dev/null
+++ b/nlp-service/models.py
@@ -0,0 +1,17 @@
+from __future__ import annotations
+from typing import Literal
+from pydantic import BaseModel
+
+
+class ParseRequest(BaseModel):
+    query: str
+    lang: Literal["de", "en", "es"]
+
+
+class ParseResponse(BaseModel):
+    personNames: list[str]
+    personRole: Literal["sender", "receiver", "any"]
+    dateFrom: str | None
+    dateTo: str | None
+    keywords: list[str]
+    rawQuery: str
diff --git a/nlp-service/requirements.txt b/nlp-service/requirements.txt
new file mode 100644
index 00000000..14c14462
--- /dev/null
+++ b/nlp-service/requirements.txt
@@ -0,0 +1,6 @@
+fastapi[standard]==0.115.6
+uvicorn[standard]==0.34.0
+spacy>=3.8,<4.0
+dateparser>=1.2,<2.0
+pytest>=8.0,<9.0
+httpx>=0.28,<1.0
diff --git a/nlp-service/test_extractor.py b/nlp-service/test_extractor.py
new file mode 100644
index 00000000..0b80d0b4
--- /dev/null
+++ b/nlp-service/test_extractor.py
@@ -0,0 +1,33 @@
+import pytest
+from pydantic import ValidationError
+
+
+# ── Models ──────────────────────────────────────────────────────────────────
+
+def test_parse_request_valid():
+    from models import ParseRequest
+    req = ParseRequest(query="Briefe von Opa", lang="de")
+    assert req.query == "Briefe von Opa"
+    assert req.lang == "de"
+
+
+def test_parse_request_rejects_unknown_lang():
+    from models import ParseRequest
+    with pytest.raises(ValidationError):
+        ParseRequest(query="Letters from grandpa", lang="fr")
+
+
+def test_parse_response_serializes_nulls():
+    from models import ParseResponse
+    resp = ParseResponse(
+        personNames=["Opa"],
+        personRole="sender",
+        dateFrom=None,
+        dateTo="1920-12-31",
+        keywords=["brief"],
+        rawQuery="Briefe von Opa",
+    )
+    data = resp.model_dump()
+    assert data["dateFrom"] is None
+    assert data["dateTo"] == "1920-12-31"
+    assert data["personRole"] == "sender"