an area LLM. Good.
However after the primary few chats, you is perhaps questioning: what else can I do with it?
Effectively, how about making the native LLM agentic with some software use?
On this publish, we’ll discover find out how to flip an area LLM right into a tool-using agent. Particularly, we’ll use
Gemma 4 mannequin (edge-friendly variants) as our native LLM
Ollama for serving the native LLM
OpenAI Brokers SDK for the agent runtime
Tavily net search MCP as one instance of the exterior software
We’ll construct a mini deep analysis agent that may search the net, collect the proof, and synthesize a solution with citations, given a consumer query.
By the tip of the publish, you’d have a working native deep analysis agent and a reusable implementation sample for turning an area mannequin into an area AI agent.
In case you are fascinated about an area coding-agent setup, I beforehand lined Gemma 4 + OpenCode. On this publish, we give attention to the extra normal sample of connecting an area mannequin to an agent runtime and exterior instruments.
1. Set Up the Native Agent Stack
We have to put together 4 items earlier than we write the code: Ollama, Gemma 4 (particularly the Gemma 4 E4B mannequin), OpenAI Brokers SDK, and Tavily MCP.
First, let’s set up Ollama.
On Home windows, you possibly can obtain the installer from the official Ollama web site:
https://ollama.com/obtain
Or use winget in PowerShell:
winget set up Ollama.Ollama
On Linux, Ollama might be put in with:
“curl -fsSL https://ollama.com/set up.sh | sh”
After set up, please examine:
ollama –version
On Home windows, bear in mind to launch Ollama from the Begin menu. As soon as it’s operating, the native API endpoint is obtainable.
Subsequent, we pull the native mannequin. Right here, we use Gemma 4 E4B variant:
ollama pull gemma4:e4b
Gemma 4 has a number of variants. The E4B mannequin is an efficient match for our function, as it’s designed with edge/native agentic workflows in thoughts. My machine has an NVIDIA RTX 2000 Ada Laptop computer GPU with about 8 GB VRAM. In case your machine is extra constrained, you possibly can strive the lighter E2B variant:
ollama pull gemma4:e2b
Subsequent, we want the agent runtime library. For that, we use OpenAI Brokers SDK:
pip set up openai-agents
You’d additionally want the OpenAI-compatible consumer:
pip set up openai
One thing to notice right here: later, we’ll level the consumer to Ollama’s native endpoint, so this doesn’t imply we’re sending mannequin calls to OpenAI.
Lastly, we want a Tavily MCP endpoint. In case you haven’t used it earlier than, Tavily is a search API designed for LLM purposes. On this publish, we use its MCP server so the agent can search the net.
You’d must first create a Tavily account and get an API key. On the Tavily platform, you possibly can instantly generate a MCP hyperlink with the next form:
https://mcp.tavily.com/mcp/?tavilyApiKey=
Now we’re prepared.
Utilizing Tavily right here is just not a sponsored alternative; it’s used right here as one handy MCP software, the identical sample can work with different MCP-compatible instruments as effectively.
The truth is, the entire stack right here is just not the one choice. As a substitute of utilizing Ollama, you might serve the native mannequin with LM Studio or llama.cpp. As a substitute of Gemma 4 fashions, you may also strive with different fashions from, e.g., Qwen household. For agent framework, we even have choices from Google or Anthropic. You may additionally join totally different MCP instruments as a substitute of Tavily. I exploit this mixture just because I’m acquainted with that stack. However the necessary takeaway on this case research is the overall native agentic sample.
2. Configure the Native Analysis Agent
With OpenAI Brokers SDK, that is the ultimate Agent object we have to compose:
from brokers import Agent
agent = Agent(
identify=”Native Analysis Agent”,
directions=RESEARCH_AGENT_INSTRUCTIONS,
mannequin=mannequin,
mcp_servers=[tavily_server],
mcp_config={“include_server_in_tool_names”: True},
)
Let’s unpack every half.
2.1 The Mannequin
First, the mannequin.
from openai import AsyncOpenAI
from brokers import OpenAIChatCompletionsModel
MODEL_NAME = “gemma4:e4b”
OLLAMA_BASE_URL = “http://localhost:11434/v1″
consumer = AsyncOpenAI(
api_key=”ollama”,
base_url=OLLAMA_BASE_URL,
)
mannequin = OpenAIChatCompletionsModel(
mannequin=MODEL_NAME,
openai_client=consumer,
)
We begin by making a consumer that factors at Ollama’s native OpenAI-compatible endpoint.
Then, we use OpenAIChatCompletionsModel to wrap the Gemma mannequin right into a mannequin object. This permits the Brokers SDK to make use of that mannequin contained in the agent loop.
Observe that the api_key=”ollama” worth is only a placeholder. Ollama doesn’t really want an actual OpenAI API key. We use it as a result of the consumer expects this area.
2.2 The Instruction
Subsequent, we outline the instruction for the agent with the specified analysis habits:
from datetime import datetime
CURRENT_DATE = datetime.now().strftime(“%B %d, %Y”)
# Observe that this instruction is iterated with AI
RESEARCH_AGENT_INSTRUCTIONS = f”””
[Role]
You’re a concise analysis assistant.
[Task]
Reply the consumer’s query by turning it right into a small net analysis process.
Use the present date when deciphering time-sensitive questions: {CURRENT_DATE}.
[Research behavior]
Begin with one focused search question.
For advice or comparability questions, full this analysis loop earlier than answering:
first determine the primary choices, then seek for comparability context, then synthesize a advice.
Use follow-up searches when the primary outcomes are inadequate, conflicting, or solely cowl a part of the query.
Want related and credible sources, and observe which supply helps every necessary declare.
Earlier than answering, examine whether or not the gathered proof is sufficient to help the conclusion.
[Expected output]
Give a direct reply first, then briefly clarify the proof behind it.
Embrace supply hyperlinks for key factual claims.
[Rules]
Don’t depend on reminiscence for information that will have modified.
Don’t invent lacking particulars.
Maintain the reply concise.
“””.strip()
2.3 The Instruments
Now we equip the agent with the net search software. On this case, we use the Tavily search engine by way of MCP:
from brokers import Agent, Runner
from brokers.mcp import MCPServerStreamableHttp
TAVILY_MCP_URL = “YOUR_TAVILY_MCP_URL”
async with MCPServerStreamableHttp(
identify=”tavily”,
params={“url”: TAVILY_MCP_URL},
) as tavily_server:
instruments = await tavily_server.list_tools()
print(“Out there Tavily instruments:”)
for software in instruments:
description = (software.description or “”).change(“n”, ” “)
print(f”- {software.identify}: {description[:120]}”)
agent = Agent(
identify=”Native Analysis Agent”,
directions=RESEARCH_AGENT_INSTRUCTIONS,
mannequin=mannequin,
mcp_servers=[tavily_server],
mcp_config={“include_server_in_tool_names”: True},
)
end result = await Runner.run(agent, RESEARCH_QUESTION, max_turns=MAX_TURNS)
This code block does three issues:
It opens a connection to Tavily’s MCP server with async with MCPServerStreamableHttp(…) as tavily_server: As soon as related, Tavily would expose its accessible instruments to the Brokers SDK.
We create the Agent object contained in the MCP context. Observe that we’ve mcp_servers=[tavily_server], which attaches Tavily’s MCP instruments to the agent.
We lastly run the agent with end result = await Runner.run(agent, RESEARCH_QUESTION, max_turns=MAX_TURNS). The context supervisor issues right here as a result of the MCP connection is barely energetic contained in the async with block.
mcp_config={“include_server_in_tool_names”: True} is principally for readability within the hint. With out it, the software identify will solely seem as tavily_search. With it, the software identify will present as mcp_tavily__tavily_search. This makes it clearer that the software name got here by way of the Tavily MCP server.
3. Run a Analysis Query
Now that the agent is configured, let’s check it with one concrete query:
“Which June 23, 2026 World Cup match had the most important group-stage stakes, and why?”
To examine what occurred, I print a compact hint:
def compact(worth: object, restrict: int = 220) -> str:
textual content = str(worth).change(“n”, ” “)
return textual content if len(textual content) <= restrict else textual content[:limit] + “…”
for step, merchandise in enumerate(end result.new_items, begin=1):
raw_item = getattr(merchandise, “raw_item”, None)
raw_type = getattr(raw_item, “sort”, “”)
raw_name = getattr(raw_item, “identify”, “”)
raw_output = getattr(raw_item, “output”, “”)
print(
f”{step:02d} | {sort(merchandise).__name__} | ”
f”{raw_type or raw_name} | {compact(raw_output or raw_item)}”
)
In my run, the hint appeared like this:
01 | ToolCallItem | function_call | ResponseFunctionToolCall(arguments='{“question”:”World Cup 2026 group stage matches June 23, 2026 stakes”}’, identify=’mcp_tavily__tavily_search’, …)
02 | ToolCallOutputItem | | {‘call_id’: …, ‘output’: …}
03 | MessageOutputItem | message | ResponseOutputMessage(… closing reply …)
This permits us to see the agentic habits instantly. On this run, the native Gemma mannequin determined to name the Tavily search software, the Brokers SDK executed that software name, and handed the outcomes again to the mannequin. Then, the mannequin produced the ultimate reply.
To see the ultimate response, we will print:
print(end result.final_output)
That is what the agent produced:
The match with the most important group-stage stakes on June 23, 2026, was Colombia vs. DR Congo.
Why:
In keeping with FIFA reporting, this particular match was highlighted as a essential second the place Colombia superior into the knockout part of the event.
The article notes that Daniel Munoz scored the primary purpose for Colombia throughout this Group Okay fixture, which instantly contributed to their development within the competitors.
Proof
– FIFA: An article titled “Colombia v Congo DR Group Okay FIFA World Cup 2026” particularly experiences on a key second from this match, stating that Munoz’s purpose helped hearth Colombia into the knockout part.
Supply: https://digitalhub.fifa.com/remodel/450614d3-72d7-4c1f-85ff-ea0fbee6f28d/Colombia-v-Congo-DR-Group-Okay-FIFA-World-Cup-2026?focuspoint=0.51
– Yahoo Sports activities: Confirms the fixture and end result for that date: Colombia defeated DR Congo.
Supply: https://sports activities.yahoo.com/soccer/article/2026-world-cup-results-standings-and-schedule-live-scores-group-stage-updates-and-how-to-watch-050724193.html
Discover that the agent solely made one search spherical on this run, because the search outcomes already contained sufficient proof for the mannequin to reply. For extra complicated questions, a number of rounds of search and reasoning could be vital, and our present framework naturally helps that.
4. Wrapping Up
An area LLM doesn’t have to remain as a chat mannequin.
On this publish, we deployed a Gemma 4 E4B mannequin regionally by way of Ollama, then we put the mannequin inside an agent runtime supplied by OpenAI Brokers SDK, and we gave the agent an online search software in order that it may discover info on-line to reply customers’ questions.
From right here, you possibly can simply prolong this sample with stronger analysis directions or construct a extra specific planning-reflection workflow, if you wish to preserve working within the course of deep analysis, or you possibly can join the agent to extra MCP instruments for a lot of different use instances.
Blissful constructing!
Reference
Ollama: https://ollama.com/
Gemma mannequin household: https://ai.google.dev/gemma
OpenAI Brokers SDK: https://openai.github.io/openai-agents-python/
Brokers SDK MCP docs: https://openai.github.io/openai-agents-python/mcp/
Tavily MCP docs: https://docs.tavily.com/documentation/mcp
