diff --git a/agent.py b/agent.py
index 8628897..7233f37 100644
--- a/agent.py
+++ b/agent.py
@@ -1,39 +1,31 @@
 """
-Agent definition using LangChain create_agent.
+Agent creation with RAG integration.
 """
-
 import os
+from typing import List
+
 from langchain_openai import ChatOpenAI
 from langchain.agents import create_agent
 from langchain_core.messages import HumanMessage
+from langgraph.checkpoint.memory import MemorySaver
 from tools import search_knowledge_base, add_to_knowledge_base
 
-# LLM – Ollama via BroJS endpoint (placeholder)
+# LLM via Ollama (llama3)
 llm = ChatOpenAI(
-    model="openai/gpt-oss-20b:free",
-    base_url="https://platform.brojs.ru/jrnl-bh/api/inference/v1",
-    api_key=os.getenv("JOURNAL_MCP_PAT"),
-    temperature=0.5,
+    model="ollama/llama3",
+    base_url="http://localhost:11434/v1",
+    api_key=None,
+    temperature=0.2,
 )
 
 agent = create_agent(
     llm=llm,
     tools=[search_knowledge_base, add_to_knowledge_base],
-    system_prompt="You are a helpful assistant with access to a knowledge base.",
+    system_prompt="You are a helpful assistant that can search and add documents to the knowledge base.",
 )
 
-async def main():
-    # Simple demo: add and search
-    await agent.ainvoke(
-        {"messages": [HumanMessage(content="Add sample text about Python")]},
-        {"configurable": {"thread_id": "demo-1"}},
-    )
-    result = await agent.ainvoke(
-        {"messages": [HumanMessage(content="Search for Python")]},
-        {"configurable": {"thread_id": "demo-1"}},
-    )
-    print(result["messages"][-1].content)
+memory = MemorySaver()
 
-if __name__ == "__main__":  # pragma: no cover
-    import asyncio
-    asyncio.run(main())
+async def run_agent(messages: List[HumanMessage]):
+    result = await agent.ainvoke({"messages": messages}, {"configurable": {"thread_id": "session-1"}})
+    return result["messages"][-1].content