diff --git a/local_llm_chat.py b/local_llm_chat.py
new file mode 100644
index 0000000..4aee7de
--- /dev/null
+++ b/local_llm_chat.py
@@ -0,0 +1,89 @@
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+
+import ollama
+
+
+DEFAULT_MODEL = "qwen2.5:3b"
+DEFAULT_FILES = [
+    "README.md",
+    "Auto_Seat.ino",
+    "upload.ps1",
+]
+
+
+def read_context(paths: list[str]) -> str:
+    chunks: list[str] = []
+    for item in paths:
+        path = Path(item)
+        if not path.exists() or not path.is_file():
+            continue
+
+        text = path.read_text(encoding="utf-8", errors="replace")
+        chunks.append(f"## {path.as_posix()}\n{text}")
+
+    return "\n\n".join(chunks)
+
+
+def ask(model: str, context: str, question: str) -> str:
+    system_prompt = (
+        "You are a local assistant for this Arduino Auto_Seat project. "
+        "Answer in Korean by default. Use the provided project context when it is relevant. "
+        "If the context does not contain the answer, say that clearly and reason from general knowledge."
+    )
+
+    if context:
+        user_prompt = f"Project context:\n{context}\n\nQuestion:\n{question}"
+    else:
+        user_prompt = question
+
+    response = ollama.chat(
+        model=model,
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_prompt},
+        ],
+    )
+    return response["message"]["content"]
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Local LLM chat for the Auto_Seat project.")
+    parser.add_argument("--model", default=DEFAULT_MODEL, help=f"Ollama model name. Default: {DEFAULT_MODEL}")
+    parser.add_argument(
+        "--no-context",
+        action="store_true",
+        help="Chat without loading project files into the prompt.",
+    )
+    args = parser.parse_args()
+
+    context = "" if args.no_context else read_context(DEFAULT_FILES)
+
+    print(f"Local LLM ready: {args.model}")
+    print("Ask anything. Type /exit to quit.")
+
+    while True:
+        try:
+            question = input("\nYou> ").strip()
+        except (EOFError, KeyboardInterrupt):
+            print()
+            break
+
+        if question.lower() in {"/exit", "/quit", "exit", "quit"}:
+            break
+        if not question:
+            continue
+
+        try:
+            answer = ask(args.model, context, question)
+        except Exception as exc:
+            print(f"\nError: {exc}")
+            continue
+
+        print(f"\nLLM> {answer}")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/run-local-llm.ps1 b/run-local-llm.ps1
new file mode 100644
index 0000000..88067a6
--- /dev/null
+++ b/run-local-llm.ps1
@@ -0,0 +1,10 @@
+$ErrorActionPreference = "Stop"
+
+$env:Path = [System.Environment]::GetEnvironmentVariable("Path", "Machine") + ";" + [System.Environment]::GetEnvironmentVariable("Path", "User")
+
+if (-not (Test-Path ".\.venv\Scripts\python.exe")) {
+    python -m venv .venv
+}
+
+.\.venv\Scripts\python.exe -m pip install -r requirements.txt
+.\.venv\Scripts\python.exe .\local_llm_chat.py