diff --git a/mem0/configs/embeddings/base.py b/mem0/configs/embeddings/base.py
index de2f4324f..2cd03dd68 100644
--- a/mem0/configs/embeddings/base.py
+++ b/mem0/configs/embeddings/base.py
@@ -34,7 +34,7 @@ class BaseEmbedderConfig(ABC):
         # Gemini specific
         output_dimensionality: Optional[str] = None,
         # LM Studio specific
-        lmstudio_base_url: Optional[str] = "http://localhost:1234/v1",
+        lmstudio_base_url: Optional[str] = None,
         # AWS Bedrock specific
         aws_access_key_id: Optional[str] = None,
         aws_secret_access_key: Optional[str] = None,
@@ -70,7 +70,8 @@ class BaseEmbedderConfig(ABC):
         :type memory_update_embedding_type: Optional[str], optional
         :param memory_search_embedding_type: The type of embedding to use for the search memory action, defaults to None
         :type memory_search_embedding_type: Optional[str], optional
-        :param lmstudio_base_url: LM Studio base URL to be use, defaults to "http://localhost:1234/v1"
+        :param lmstudio_base_url: LM Studio base URL to be use, defaults to None
+            (resolved by the provider from LMSTUDIO_BASE_URL, then "http://localhost:1234/v1")
         :type lmstudio_base_url: Optional[str], optional
         """
 
diff --git a/mem0/embeddings/lmstudio.py b/mem0/embeddings/lmstudio.py
index f8943e430..606d39da4 100644
--- a/mem0/embeddings/lmstudio.py
+++ b/mem0/embeddings/lmstudio.py
@@ -1,3 +1,4 @@
+import os
 from typing import Literal, Optional
 
 from openai import OpenAI
@@ -13,6 +14,9 @@ class LMStudioEmbedding(EmbeddingBase):
         self.config.model = self.config.model or "nomic-ai/nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf"
         self.config.embedding_dims = self.config.embedding_dims or 1536
         self.config.api_key = self.config.api_key or "lm-studio"
+        self.config.lmstudio_base_url = (
+            self.config.lmstudio_base_url or os.getenv("LMSTUDIO_BASE_URL") or "http://localhost:1234/v1"
+        )
 
         self.client = OpenAI(base_url=self.config.lmstudio_base_url, api_key=self.config.api_key)
 
diff --git a/tests/embeddings/test_lm_studio_embeddings.py b/tests/embeddings/test_lm_studio_embeddings.py
index c391fc389..6f33384a5 100644
--- a/tests/embeddings/test_lm_studio_embeddings.py
+++ b/tests/embeddings/test_lm_studio_embeddings.py
@@ -6,7 +6,6 @@ from mem0.configs.embeddings.base import BaseEmbedderConfig
 from mem0.embeddings.lmstudio import LMStudioEmbedding
 
 
-
 @pytest.fixture
 def mock_lm_studio_client():
     with patch("mem0.embeddings.lmstudio.OpenAI") as mock_openai:
@@ -80,3 +79,31 @@ def test_embed_batch_count_mismatch_raises(mock_lm_studio_client):
 
     with pytest.raises(ValueError, match="returned 1 embeddings for 2 texts"):
         embedder.embed_batch(["first text", "second text"])
+
+
+def test_base_url_honors_lmstudio_base_url_env(mock_lm_studio_client, monkeypatch):
+    monkeypatch.setenv("LMSTUDIO_BASE_URL", "http://lmstudio.internal:9000/v1")
+
+    with patch("mem0.embeddings.lmstudio.OpenAI") as mock_openai:
+        LMStudioEmbedding(BaseEmbedderConfig())
+
+    assert mock_openai.call_args.kwargs["base_url"] == "http://lmstudio.internal:9000/v1"
+
+
+def test_base_url_prefers_explicit_config_over_env(mock_lm_studio_client, monkeypatch):
+    monkeypatch.setenv("LMSTUDIO_BASE_URL", "http://lmstudio.internal:9000/v1")
+
+    with patch("mem0.embeddings.lmstudio.OpenAI") as mock_openai:
+        LMStudioEmbedding(BaseEmbedderConfig(lmstudio_base_url="http://explicit:1234/v1"))
+
+    assert mock_openai.call_args.kwargs["base_url"] == "http://explicit:1234/v1"
+
+
+def test_base_url_falls_back_to_localhost_default(mock_lm_studio_client, monkeypatch):
+    monkeypatch.delenv("LMSTUDIO_BASE_URL", raising=False)
+
+    with patch("mem0.embeddings.lmstudio.OpenAI") as mock_openai:
+        embedder = LMStudioEmbedding(BaseEmbedderConfig())
+
+    assert mock_openai.call_args.kwargs["base_url"] == "http://localhost:1234/v1"
+    assert embedder.config.lmstudio_base_url == "http://localhost:1234/v1"