diff --git a/reme/components/file_store/local_file_store.py b/reme/components/file_store/local_file_store.py
index 86d94177..4ccd76cf 100644
--- a/reme/components/file_store/local_file_store.py
+++ b/reme/components/file_store/local_file_store.py
@@ -91,9 +91,31 @@ class LocalFileStore(BaseFileStore):
                     self.file_chunks[chunk.id] = chunk
             self.logger.info(f"Loaded {len(self.file_chunks)} chunks from {self.chunks_path}")
             await self._sync_keyword_index_from_chunks()
+            await self._backfill_missing_embeddings()
         except Exception as e:
             self.logger.exception(f"Failed to load {self.chunks_path}: {e}")
 
+    async def _backfill_missing_embeddings(self) -> None:
+        """Embed persisted chunks that predate embedding being enabled."""
+        if not self.embedding_store or not self.file_chunks:
+            return
+
+        missing = [chunk for chunk in self.file_chunks.values() if chunk.text and chunk.embedding is None]
+        if not missing:
+            return
+
+        self.logger.info(f"{self.name}: backfilling embeddings for {len(missing)} chunks")
+        try:
+            await self.embedding_store.get_node_embeddings(missing)
+        except Exception as e:
+            self._disable_embedding(f"backfill: {type(e).__name__}: {e}")
+            return
+
+        filled = sum(1 for chunk in missing if chunk.embedding is not None)
+        if filled:
+            self.logger.info(f"{self.name}: backfilled embeddings for {filled}/{len(missing)} chunks")
+            await self.dump()
+
     async def _sync_keyword_index_from_chunks(self) -> None:
         """Repair keyword index when its persisted state does not match chunks."""
         if not self.keyword_index or not self.file_chunks:
diff --git a/tests/unit/test_file_store_consistency.py b/tests/unit/test_file_store_consistency.py
index 6ddd1a97..8d42c070 100644
--- a/tests/unit/test_file_store_consistency.py
+++ b/tests/unit/test_file_store_consistency.py
@@ -140,6 +140,39 @@ def test_same_chunk_id_with_changed_text_gets_new_embedding():
     run(go())
 
 
+def test_load_backfills_missing_embeddings_from_persisted_chunks():
+    """Loading old chunks after enabling embeddings backfills and persists vectors."""
+
+    async def go():
+        with tempfile.TemporaryDirectory() as tmp, temp_chdir(tmp):
+            store = LocalFileStore(name="t_embedding_backfill", embedding_store="")
+            await store.start()
+            await store.upsert(
+                [
+                    (node("a.md"), [chunk("a", "a.md", "alpha text")]),
+                    (node("b.md"), [chunk("b", "b.md", "fresh beta text")]),
+                ],
+            )
+            await store.close()
+
+            store = LocalFileStore(name="t_embedding_backfill", embedding_store="")
+            await store.start()
+            store.embedding_store = FakeEmbeddingStore()
+            await store.load()
+
+            assert store.file_chunks["a"].embedding.tolist() == [1.0, 0.0]
+            assert store.file_chunks["b"].embedding.tolist() == [0.0, 1.0]
+            await store.close()
+
+            store = LocalFileStore(name="t_embedding_backfill", embedding_store="")
+            await store.start()
+            assert store.file_chunks["a"].embedding.tolist() == [1.0, 0.0]
+            assert store.file_chunks["b"].embedding.tolist() == [0.0, 1.0]
+            await store.close()
+
+    run(go())
+
+
 def test_search_filter_applies_to_vector_and_keyword_results():
     """Search filters apply consistently to vector and keyword results."""