diff --git a/main.py b/main.py
new file mode 100644
index 0000000..206382c
--- /dev/null
+++ b/main.py
@@ -0,0 +1,121 @@
+import os
+import asyncio
+import json
+import httpx
+from pathlib import Path
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_chroma import Chroma
+from langchain_core.documents import Document
+from langchain.tools import tool
+from deepagents import create_deep_agent
+from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
+from langchain_core.messages import HumanMessage
+
+# ---------- Configuration ----------
+DATA_DIR = Path("data")
+CHROMA_DIR = Path("./chroma_faq")
+CHROMA_COLLECTION = "faq_collection"
+MOCK_META_URL = "http://localhost:8000/meta.json"  # change if you use a different mock
+
+# ---------- Embeddings and LLM ----------
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
+)
+
+llm = ChatOpenAI(
+    model="openai/gpt-oss-20b:free",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
+    temperature=0.0,
+)
+
+# ---------- Chroma setup ----------
+vector_store = Chroma(
+    collection_name=CHROMA_COLLECTION,
+    embedding_function=embeddings,
+    persist_directory=str(CHROMA_DIR),
+)
+
+# ---------- Load FAQ into Chroma ----------
+
+def load_faq_to_chroma():
+    if not CHROMA_DIR.exists():
+        CHROMA_DIR.mkdir(parents=True, exist_ok=True)
+    # If collection already exists, skip loading
+    if vector_store.get_collection().count() > 0:
+        return
+    docs = []
+    for md_file in DATA_DIR.glob("*.md"):
+        text = md_file.read_text(encoding="utf-8")
+        docs.append(Document(page_content=text, metadata={"source": md_file.name}))
+    vector_store.add_documents(docs)
+    vector_store.persist()
+
+# ---------- Tools ----------
+@tool
+def search_course_docs(query: str, k: int = 3) -> str:
+    """Search local course documents in Chroma and return top k snippets."""
+    results = vector_store.similarity_search(query, k=k)
+    snippets = [f"{res.metadata.get('source', 'unknown')}\n{res.page_content[:200]}..." for res in results]
+    return "\n\n".join(snippets)
+
+@tool
+def fetch_course_meta(query: str) -> str:
+    """Mock MCP tool that fetches course metadata from a local JSON endpoint."""
+    try:
+        response = httpx.get(MOCK_META_URL, timeout=5)
+        response.raise_for_status()
+        data = response.json()
+        # Simple filtering: return items that contain the query string (case-insensitive)
+        matches = [item for item in data if query.lower() in json.dumps(item).lower()]
+        return json.dumps(matches, indent=2) if matches else "No metadata found for the query."
+    except Exception as e:
+        return f"Error fetching metadata: {e}"
+
+# ---------- Backend ----------
+backend = CompositeBackend(
+    default=LocalShellBackend(root_dir="./workspace", virtual_mode=True, inherit_env=True),
+    routes={},
+)
+
+# ---------- Agent ----------
+agent = create_deep_agent(
+    model=llm,
+    tools=[search_course_docs, fetch_course_meta],
+    backend=backend,
+    system_prompt="You are a helpful course assistant. Use the search_course_docs tool for questions about lecture materials and fetch_course_meta for schedule or metadata questions. In your answer, prepend 'source: chroma' or 'source: mcp_meta' to indicate the used tool.",
+)
+
+# ---------- CLI ----------
+PRESET_QUESTIONS = [
+    "What topics are covered in Lecture 3?",  # should use chroma
+    "Explain the concept of tokenization in NLP.",  # chroma
+    "When is the next midterm exam scheduled?",  # mcp_meta
+]
+
+async def run_agent(question: str, thread_id: str = "session-1"):
+    result = await agent.ainvoke(
+        {"messages": [HumanMessage(content=question)]},
+        {"configurable": {"thread_id": thread_id}},
+    )
+    return result["messages"][-1].content
+
+async def main():
+    load_faq_to_chroma()
+    print("--- FAQ Bot Demo ---")
+    for i, q in enumerate(PRESET_QUESTIONS, 1):
+        print(f"\nQuestion {i}: {q}")
+        answer = await run_agent(q, thread_id=f"demo-{i}")
+        print("Answer:\n", answer)
+    print("\nEnter your own question (or type 'exit' to quit):")
+    while True:
+        user_q = input("> ")
+        if user_q.lower() in {"exit", "quit"}:
+            break
+        answer = await run_agent(user_q, thread_id="interactive")
+        print("Answer:\n", answer)
+
+if __name__ == "__main__":
+    asyncio.run(main())