diff --git a/.gitignore b/.gitignore
index bd15bf3..3dacaa0 100644
--- a/.gitignore
+++ b/.gitignore
@@ -8,5 +8,5 @@ __pycache__/
 build/
 dist/
 *.egg-info/
-
+*.md
 env.sh
diff --git a/laser/main.py b/laser/main.py
index 8f58d4b..0de68b1 100644
--- a/laser/main.py
+++ b/laser/main.py
@@ -26,6 +26,13 @@
     "google": (GoogleGenAI, {}),
     "openai": (OpenAIResponses, {}),
     "chat": (OpenAILegacy, {}),
+    "litellm": (
+        OpenAILegacy,
+        {
+            "base_url": os.getenv("LITELLM_PROXY_API_BASE", "http://localhost:4000"),
+            "api_key": os.getenv("LITELLM_PROXY_API_KEY"),
+        },
+    ),
 }
 
 SYSTEM_PROMPT = """You are Laser, a coding agent for this repository.
@@ -73,7 +80,7 @@ def parse_args():
     parser.add_argument(
         "--model",
         default="openai/gpt-5.2",
-        help="Model identifier to use in the form <provider>/<model>",
+        help="Model identifier to use in the form <provider>/<model>. Providers: anthropic, google, openai, chat, litellm",
     )
     parser.add_argument(
         "--max-tokens",
@@ -217,6 +224,10 @@ def build_provider(model: str, max_tokens: int) -> ChatProvider:
     provider_cls, provider_kwargs = PROVIDER_CONFIGS[provider]
     if provider_cls is Anthropic:
         provider_kwargs = {**provider_kwargs, "default_max_tokens": max_tokens}
+    if provider == "litellm":
+        env_model = os.getenv("LITELLM_MODEL")
+        if env_model:
+            model_name = env_model
     return provider_cls(model=model_name, **provider_kwargs)
 
 
diff --git a/run.sh b/run.sh
new file mode 100755
index 0000000..13d47fc
--- /dev/null
+++ b/run.sh
@@ -0,0 +1,14 @@
+export LITELLM_MODEL=glm-4.7
+export LITELLM_PROXY_API_KEY=sk-1234
+export LITELLM_PROXY_API_BASE=http://192.168.43.179:4001
+uv run laser --model litellm/glm-4.7 $@
+
+exit
+
+o use:
+
+$: uv tool install git+https://github.com/ExpressGradient/laser
+$: laser
+
+or 
+$: uvx --from git+https://github.com/ExpressGradient/laser laser
\ No newline at end of file