diff --git a/src/memos/api/config.py b/src/memos/api/config.py
index d2dd19266..65049b0c2 100644
--- a/src/memos/api/config.py
+++ b/src/memos/api/config.py
@@ -1014,6 +1014,7 @@ def create_user_config(user_name: str, user_id: str) -> tuple["MOSConfig", "Gene
                                 "fast_graph": bool(os.getenv("FAST_GRAPH", "false") == "true"),
                                 "bm25": bool(os.getenv("BM25_CALL", "false") == "true"),
                                 "cot": bool(os.getenv("VEC_COT_CALL", "false") == "true"),
+                                "fulltext": bool(os.getenv("FULLTEXT_CALL", "false") == "true"),
                             },
                             "include_embedding": bool(
                                 os.getenv("INCLUDE_EMBEDDING", "false") == "true"
@@ -1096,6 +1097,7 @@ def get_default_cube_config() -> "GeneralMemCubeConfig | None":
                                 "fast_graph": bool(os.getenv("FAST_GRAPH", "false") == "true"),
                                 "bm25": bool(os.getenv("BM25_CALL", "false") == "true"),
                                 "cot": bool(os.getenv("VEC_COT_CALL", "false") == "true"),
+                                "fulltext": bool(os.getenv("FULLTEXT_CALL", "false") == "true"),
                             },
                             "mode": os.getenv("ASYNC_MODE", "sync"),
                             "include_embedding": bool(
diff --git a/src/memos/graph_dbs/neo4j.py b/src/memos/graph_dbs/neo4j.py
index 23ce2408b..746051187 100644
--- a/src/memos/graph_dbs/neo4j.py
+++ b/src/memos/graph_dbs/neo4j.py
@@ -928,6 +928,26 @@ def search_by_embedding(
 
         return records
 
+    def search_by_fulltext(
+        self,
+        query_words: list[str],
+        top_k: int = 10,
+        scope: str | None = None,
+        status: str | None = None,
+        threshold: float | None = None,
+        search_filter: dict | None = None,
+        user_name: str | None = None,
+        filter: dict | None = None,
+        knowledgebase_ids: list[str] | None = None,
+        tsquery_config: str | None = None,
+        **kwargs,
+    ) -> list[dict]:
+        """
+        TODO: 实现 Neo4j 的关键词检索, 以兼容 TreeTextMemory 的 keyword/fulltext 召回路径.
+        目前先返回空列表, 避免切换到 Neo4j 后因缺失方法导致运行时报错.
+        """
+        return []
+
     def get_by_metadata(
         self,
         filters: list[dict[str, Any]],
diff --git a/src/memos/graph_dbs/neo4j_community.py b/src/memos/graph_dbs/neo4j_community.py
index e34313fa2..cae7d6ca5 100644
--- a/src/memos/graph_dbs/neo4j_community.py
+++ b/src/memos/graph_dbs/neo4j_community.py
@@ -382,6 +382,26 @@ def search_by_embedding(
 
         return filtered_results
 
+    def search_by_fulltext(
+        self,
+        query_words: list[str],
+        top_k: int = 10,
+        scope: str | None = None,
+        status: str | None = None,
+        threshold: float | None = None,
+        search_filter: dict | None = None,
+        user_name: str | None = None,
+        filter: dict | None = None,
+        knowledgebase_ids: list[str] | None = None,
+        tsquery_config: str | None = None,
+        **kwargs,
+    ) -> list[dict]:
+        """
+        TODO: 实现 Neo4j Community 的关键词检索, 以兼容 TreeTextMemory 的 keyword/fulltext 召回路径.
+        目前先返回空列表, 避免切换到 Neo4j 后因缺失方法导致运行时报错.
+        """
+        return []
+
     def _normalize_date_string(self, date_str: str) -> str:
         """
         Normalize date string to ISO 8601 format for Neo4j datetime() function.
diff --git a/src/memos/memories/textual/tree_text_memory/retrieve/searcher.py b/src/memos/memories/textual/tree_text_memory/retrieve/searcher.py
index f00efccb6..9dcbe8c56 100644
--- a/src/memos/memories/textual/tree_text_memory/retrieve/searcher.py
+++ b/src/memos/memories/textual/tree_text_memory/retrieve/searcher.py
@@ -67,6 +67,7 @@ def __init__(
         self.internet_retriever = internet_retriever
         self.vec_cot = search_strategy.get("cot", False) if search_strategy else False
         self.use_fast_graph = search_strategy.get("fast_graph", False) if search_strategy else False
+        self.use_fulltext = search_strategy.get("fulltext", False) if search_strategy else False
         self.manual_close_internet = manual_close_internet
         self.tokenizer = tokenizer
         self._usage_executor = ContextThreadPoolExecutor(max_workers=4, thread_name_prefix="usage")
@@ -380,20 +381,21 @@ def _retrieve_paths(
                     user_name,
                 )
             )
-            tasks.append(
-                executor.submit(
-                    self._retrieve_from_keyword,
-                    query,
-                    parsed_goal,
-                    query_embedding,
-                    top_k,
-                    memory_type,
-                    search_filter,
-                    search_priority,
-                    user_name,
-                    id_filter,
+            if self.use_fulltext:
+                tasks.append(
+                    executor.submit(
+                        self._retrieve_from_keyword,
+                        query,
+                        parsed_goal,
+                        query_embedding,
+                        top_k,
+                        memory_type,
+                        search_filter,
+                        search_priority,
+                        user_name,
+                        id_filter,
+                    )
                 )
-            )
             if search_tool_memory:
                 tasks.append(
                     executor.submit(
@@ -511,16 +513,22 @@ def _retrieve_from_keyword(
 
         id_to_score: dict[str, float] = {}
         for scope in scopes:
-            hits = self.graph_store.search_by_fulltext(
-                query_words=tsquery_terms,
-                top_k=top_k * 2,
-                status="activated",
-                scope=scope,
-                search_filter=None,
-                filter=search_filter,
-                user_name=user_name,
-                tsquery_config="jiebaqry",
-            )
+            try:
+                hits = self.graph_store.search_by_fulltext(
+                    query_words=tsquery_terms,
+                    top_k=top_k * 2,
+                    status="activated",
+                    scope=scope,
+                    search_filter=None,
+                    filter=search_filter,
+                    user_name=user_name,
+                    tsquery_config="jiebaqry",
+                )
+            except Exception as e:
+                logger.warning(
+                    f"[PATH-KEYWORD] search_by_fulltext failed, scope={scope}, user_name={user_name}"
+                )
+                hits = []
             for h in hits or []:
                 hid = str(h.get("id") or "").strip().strip("'\"")
                 if not hid: