Skip to main content

​
Integrating Agno with MLflow

MLflow provides built-in GenAI tracing so you can capture, explore, and analyze LLM and agent traces. Agno integrates directly with MLflow via a single call to mlflow.agno.autolog().

​
Prerequisites

  1. Install Dependencies Ensure the required packages are installed: 
    pip install -U mlflow agno opentelemetry-exporter-otlp openinference-instrumentation-agno
  2. Start the MLflow tracking server Start the MLflow tracking server to view traces as you run your code: 
    mlflow server
    For more information on how to host an MLflow server, see the MLflow documentation.
    If you don’t want to self-host an MLflow server, you can use Managed MLflow offered by various cloud providers.

​
Set Environment Variables

Set the environment variables for the MLflow server URL and experiment name: 
export MLFLOW_TRACKING_URI="http://localhost:5000"
export MLFLOW_EXPERIMENT_NAME="Agno Agent"
Alternatively, you can set these in your code using Python APIs. If you do this, you must call this before calling mlflow.agno.autolog(). 
import mlflow

mlflow.set_tracking_uri("http://localhost:5000")
mlflow.set_experiment("Agno Agent")

​
Enable Automatic Tracing in Your Code

Call mlflow.agno.autolog() once at startup, then use your Agno agent as usual. MLflow will automatically record traces of model/tool calls and agent steps. 
import mlflow
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.yfinance import YFinanceTools

# Enable MLflow tracing for Agno
mlflow.agno.autolog()

# Create and use the agent
agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[YFinanceTools()],
    instructions="Use tables to display data. Don't include any other text.",
    markdown=True,
)
agent.print_response("What is the stock price of Apple?", stream=False)

​
View Traces

Access the MLflow UI to view the traces. If you started the UI locally, open http://127.0.0.1:5000 in your browser. If you are using a managed MLflow server, you can access the UI at the URL provided by the cloud provider.
Agno traces in MLflow

​
AgentOS example

You can instrument your AgentOS application with MLflow by using the same approach as above. Simply call mlflow.agno.autolog() before creating your AgentOS instance.
agno_assist.py
import mlflow
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.anthropic import Claude
from agno.os import AgentOS
from agno.tools.mcp import MCPTools

# Setup automatic tracing for Agno
mlflow.agno.autolog()

agno_assist = Agent(
    name="Agno Assist",
    model=Claude(id="claude-sonnet-4-5"),
    db=SqliteDb(db_file="agno.db"),                     # session storage
    tools=[MCPTools(url="https://docs.agno.com/mcp")],  # Agno docs via MCP
    add_datetime_to_context=True,
    add_history_to_context=True,                         # include past runs
    num_history_runs=3,                                  # last 3 conversations
    markdown=True,
)

# Serve via AgentOS → streaming, auth, session isolation, API endpoints
agent_os = AgentOS(agents=[agno_assist], tracing=True)
app = agent_os.get_app()
Then run your AgentOS application following the instructions. MLflow will automatically record traces of model/tool calls and agent steps.
Agno traces in MLflow

​
Notes

  • Ensure your model provider credentials (for example, OPENAI_API_KEY) are set in the environment.
  • For best results, use the latest MLflow version that includes the Agno autolog integration.