MLflow

Integrate Agno with MLflow to automatically capture OpenTelemetry-native traces from your agents with a single line of code.

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.

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.

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.