Introduction

Agno is a powerful framework for building autonomous AI agents that can reason, use tools, maintain memory, and access knowledge bases. Portkey enhances Agno agents with enterprise-grade capabilities for production deployments.

Portkey transforms your Agno agents into production-ready systems by providing:

  • Complete observability of agent reasoning, tool usage, and knowledge retrieval
  • Access to 1600+ LLMs through a unified interface
  • Built-in reliability with fallbacks, retries, and load balancing
  • Cost tracking and optimization across all agent operations
  • Advanced guardrails for safe and compliant agent behavior
  • Enterprise governance with budget controls and access management

Agno AI Official Documentation

Learn more about Agno’s agent framework and core concepts

Setting Up Portkey

If this is your first time using Portkey, you will need to connect your LLM Provider in the app to use them in your Agno AI agents.

1

Create an Integration

Navigate to the Integrations section on Portkey’s Sidebar. This is where you’ll connect your LLM providers.

  1. Find your preferred provider (e.g., OpenAI, Anthropic, etc.)
  2. Click Connect on the provider card
  3. In the “Create New Integration” window:
    • Enter a Name for reference
    • Enter a Slug for the integration
    • Enter your API Key and other provider specific details for the provider
  4. Click Next Step

In your next step you’ll see workspace provisioning options. You can select the default “Shared Team Workspace” if this is your first time OR chose your current one.

2

Configure Models

On the model provisioning page:

  • Leave all models selected (or customize)
  • Toggle Automatically enable new models if desired

Click Create Integration to complete the integration

3

Copy the Provider Slug

Once your Integration is created:

  1. Go to Model CatalogAI Providers tab
  2. Find your integration
  3. Copy the slug (e.g., openai-dev)

This slug is your provider’s unique identifier - you’ll need it for the next step.

Quickstart

You will need

  • Portkey API Key & Portkey AI Provider slug from Step 1
1

Install required packages

pip install -U agno portkey-ai
2

Get your Portkey API Key

Sign up at app.portkey.ai to get your API key.

Once you are on the Portkey follow this guide to create your first AI provider and integration that will help us connect Agno to any LLM provider.

3

Configure Portkey with Agno

Agno makes integration incredibly simple - just use the OpenAILike model class with Portkey’s configuration:

from agno.models.openai.like import OpenAILike

portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",  # you need to use "@provider-slug/model-name" for any provider
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
)

Simple E2E example agent

Let’s create a simple Agno agent that uses Portkey for LLM calls:

simple_agent.py
from agno.agent import Agent
from agno.models.openai.like import OpenAILike

# Configure Portkey as the model provider
portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",  # You can use any model available on Portkey
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
)

# Create an Agno agent with Portkey
agent = Agent(
    model=portkey_model,
    instructions="Be concise and informative.",
    markdown=True,
)

# Run the agent
agent.print_response("What is Portkey AI?", stream=True)

Visit your Portkey dashboard to see detailed logs of your agent’s execution, including tool calls and model responses!

Production Features

1. Enhanced Observability

Portkey provides comprehensive observability for your Agno agents, helping you understand exactly what’s happening during each execution.

Traces provide a hierarchical view of your agent’s execution, showing the sequence of LLM calls, tool invocations, and state transitions.

from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from portkey_ai import createHeaders

# Add tracing to your Agno agents
portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
    default_headers=createHeaders(
        trace_id="unique_execution_trace_id",  # Add unique trace ID
    )
)

agent = Agent(
    model=portkey_model,
    instructions="You are a helpful assistant.",
    markdown=True
)

2. Reliability - Keep Your Agents Running Smoothly

When running agents in production, things can go wrong - API rate limits, network issues, or provider outages. Portkey’s reliability features ensure your agents keep running smoothly even when problems occur.

It’s this simple to enable fallback in your Agno agents:

from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from portkey_ai import createHeaders

# Create a config with fallbacks
# It's recommended that you create the Config in Portkey App rather than hard-code the config JSON directly
config = {
  "strategy": {
    "mode": "fallback"
  },
  "targets": [
    {
      "override_params": {"model": "@opeani-provider-slug/gpt-4o"}
    },
    {
      "override_params": {"model": "claude-3-opus-20240229"}
    }
  ]
}

# Configure Portkey model with fallback config
portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
    default_headers=createHeaders(config=config)
)

agent = Agent(
    model=portkey_model,
    instructions="You are a helpful assistant.",
    markdown=True
)

This configuration will automatically try Claude if the GPT-4o request fails, ensuring your agent can continue operating.

3. Prompting in Agno Agents

Portkey’s Prompt Engineering Studio helps you create, manage, and optimize the prompts used in your Agno agents. Instead of hardcoding prompts or instructions, use Portkey’s prompt rendering API to dynamically fetch and apply your versioned prompts.

Manage prompts in Portkey's Prompt Library

Prompt Playground is a place to compare, test and deploy perfect prompts for your AI application. It’s where you experiment with different models, test variables, compare outputs, and refine your prompt engineering strategy before deploying to production. It allows you to:

  1. Iteratively develop prompts before using them in your agents
  2. Test prompts with different variables and models
  3. Compare outputs between different prompt versions
  4. Collaborate with team members on prompt development

This visual environment makes it easier to craft effective prompts for each step in your Agno agent’s workflow.

Prompt Engineering Studio

Learn more about Portkey’s prompt management features

4. Guardrails for Safe Agents

Guardrails ensure your Agno agents operate safely and respond appropriately in all situations.

Why Use Guardrails?

Agno agents can experience various failure modes:

  • Generating harmful or inappropriate content
  • Leaking sensitive information like PII
  • Hallucinating incorrect information
  • Generating outputs in incorrect formats

Portkey’s guardrails protect against these issues by validating both inputs and outputs.

Implementing Guardrails

from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from portkey_ai import createHeaders

# Create a config with input and output guardrails
# It's recommended you create Config in Portkey App and pass the config ID in the client
config = {
    "input_guardrails": ["guardrails-id-xxx", "guardrails-id-yyy"],
    "output_guardrails": ["guardrails-id-xxx"]
}

# Configure Agno model with guardrails
portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
    default_headers=createHeaders(
        config=config,
    )
)

agent = Agent(
    model=portkey_model,
    instructions="You are a helpful assistant that provides safe responses.",
    markdown=True
)

Portkey’s guardrails can:

  • Detect and redact PII in both inputs and outputs
  • Filter harmful or inappropriate content
  • Validate response formats against schemas
  • Check for hallucinations against ground truth
  • Apply custom business logic and rules

Learn More About Guardrails

Explore Portkey’s guardrail features to enhance agent safety

5. User Tracking with Metadata

Track individual users through your Agno agents using Portkey’s metadata system.

What is Metadata in Portkey?

Metadata allows you to associate custom data with each request, enabling filtering, segmentation, and analytics. The special _user field is specifically designed for user tracking.

from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from portkey_ai import createHeaders

# Configure model with user tracking
portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
    default_headers=createHeaders(
        metadata={
            "_user": "user_123",  # Special _user field for user analytics
            "user_name": "John Doe",
            "user_tier": "premium",
            "user_company": "Acme Corp"
        }
    )
)

agent = Agent(
    model=portkey_model,
    user_id="user_123",  # Also use Agno's user_id for agent-level tracking
    instructions="You are a personalized assistant.",
    markdown=True
)

Filter Analytics by User

With metadata in place, you can filter analytics by user and analyze performance metrics on a per-user basis:

Filter analytics by user

This enables:

  • Per-user cost tracking and budgeting
  • Personalized user analytics
  • Team or organization-level metrics
  • Environment-specific monitoring (staging vs. production)

Learn More About Metadata

Explore how to use custom metadata to enhance your analytics

6. Caching for Efficient Agents

Implement caching to make your Agno agents more efficient and cost-effective:

from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from portkey_ai import createHeaders

portkey_config = {
  "cache": {
    "mode": "simple"
  },
}

# Configure Agno model with caching
portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
    default_headers=createHeaders(config=portkey_config)
)

agent = Agent(
    model=portkey_model,
    instructions="You are a helpful assistant.",
    markdown=True
)

Simple caching performs exact matches on input prompts, caching identical requests to avoid redundant model executions.

7. Model Interoperability: using different LLMs

One of Portkey’s key strengths is providing access to 1600+ LLMs through a unified interface. Here’s how to use different providers with Agno:

Supported Providers

See the full list of LLM providers supported by Portkey

portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
)

End-to-End Examples

Level 1: Agent with Tools and Observability

Let’s build an agent that uses tools while leveraging Portkey’s observability features:

agent_with_tools.py
from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from agno.tools.yfinance import YFinanceTools
from portkey_ai import createHeaders

# Configure Portkey with enhanced tracking
portkey_model = OpenAILike(
    id="@anthropic/claude-3-sonnet-20240320",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
    default_headers=createHeaders(
        trace_id="agno_finance_agent",
        metadata={
            "agent_type": "financial_analyst",
            "environment": "production"
        }
    )
)

agent = Agent(
    name="Financial Analyst",
    model=portkey_model,
    tools=[
        YFinanceTools(
            stock_price=True,
            company_info=True,
            analyst_recommendations=True,
            company_news=True
        )
    ],
    instructions=[
        "Provide comprehensive financial analysis",
        "Use tables for numerical data",
        "Include relevant news and recommendations",
        "Be concise but thorough"
    ],
    markdown=True,
    debug_mode=True  # See detailed agent reasoning
)

# Run analysis
agent.print_response(
    "Analyze Tesla's current financial position and recent performance",
    stream=True
)

Level 2: Agent with Knowledge Base and Caching

Enhance your Agno agent with knowledge retrieval while using Portkey’s caching to optimize costs:

agent_with_knowledge.py
from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from agno.knowledge.url import UrlKnowledge
from agno.vectordb.lancedb import LanceDb, SearchType
from agno.embedder.openai import OpenAIEmbedder
from agno.storage.sqlite import SqliteStorage
from portkey_ai import createHeaders

# Configure Portkey with caching
cache_config = {
    "cache": {
        "mode": "semantic",
        "max_age": 3600  # Cache for 1 hour
    }
}

portkey_model = OpenAILike(
    id="opeani-provider-slug/gpt-4o",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
    default_headers=createHeaders(
        config=cache_config,
        metadata={"agent_type": "knowledge_assistant"}
    )
)

# Set up knowledge base
knowledge = UrlKnowledge(
    urls=["https://docs.agno.com/introduction.md"],
    vector_db=LanceDb(
        uri="tmp/lancedb",
        table_name="agno_docs",
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(id="text-embedding-3-small", dimensions=1536),
    ),
)

# Configure storage
storage = SqliteStorage(table_name="agent_sessions", db_file="tmp/agent.db")

agent = Agent(
    name="Agno Assistant",
    model=portkey_model,
    knowledge=knowledge,
    storage=storage,
    instructions=[
        "Always search the knowledge base before answering",
        "Provide accurate information from the documentation",
        "If information isn't found, clearly state that"
    ],
    add_history_to_messages=True,
    num_history_runs=5,
    markdown=True
)

if __name__ == "__main__":
    # Load knowledge base (only needed first time)
    agent.knowledge.load(recreate=False)

    # Ask questions - responses will be cached by Portkey
    agent.print_response("What are the key features of Agno?", stream=True)

Level 3: Agent with Memory, Reasoning, and Reliability

Build a sophisticated agent that leverages Agno’s advanced features with Portkey’s reliability configurations:

advanced_agent.py
from agno.agent import Agent
from agno.models.openai.like import OpenAILike
from agno.memory.v2.memory import Memory
from agno.memory.v2.db.sqlite import SqliteMemoryDb
from agno.tools.reasoning import ReasoningTools
from agno.tools.yfinance import YFinanceTools
from portkey_ai import createHeaders

# Configure Portkey with fallbacks and retries
reliability_config = {
    "strategy": {
        "mode": "fallback"
    },
    "targets": [
        {
            "override_params": {"model": "@opeani-provider-slug/gpt-4o"}
        },
        {
            "override_params": {"model": "@anthropic-provider-slug/@anthropic-provider-slug/claude-3-opus-20240229"}
        }
    ],
    "retry": {
        "attempts": 3,
        "delay": 2
    }
}

portkey_model = OpenAILike(
    id="@opeani-provider-slug/gpt-4o",
    api_key="YOUR_PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1",
    default_headers=createHeaders(
        config=reliability_config,
        trace_id="advanced_trading_agent"
    )
)

# Set up memory
memory = Memory(
    model=portkey_model,
    db=SqliteMemoryDb(table_name="user_memories", db_file="tmp/agent.db"),
    delete_memories=True,
    clear_memories=True,
)

agent = Agent(
    name="Trading Assistant",
    model=portkey_model,
    tools=[
        ReasoningTools(add_instructions=True),
        YFinanceTools(
            stock_price=True,
            analyst_recommendations=True,
            company_info=True,
            company_news=True
        ),
    ],
    user_id="trader_1",
    instructions=[
        "Remember user preferences and trading patterns",
        "Use reasoning to analyze market conditions",
        "Provide data-driven recommendations",
        "Display results in clear tables"
    ],
    memory=memory,
    enable_agentic_memory=True,
    markdown=True,
)

if __name__ == "__main__":
    # First interaction - agent learns preferences
    agent.print_response(
        "I'm interested in tech stocks, particularly AI companies like NVIDIA and Microsoft",
        stream=True,
        show_full_reasoning=True,
    )

    # Second interaction - agent uses memory
    agent.print_response(
        "Based on my interests, what stocks should I watch today?",
        stream=True,
        show_full_reasoning=True,
    )

Set Up Enterprise Governance for Agno AI agents

Why Enterprise Governance? If you are using Agno AI agents inside your orgnaization, you need to consider several governance aspects:

  • Cost Management: Controlling and tracking AI spending across teams
  • Access Control: Managing which teams can use specific models
  • Usage Analytics: Understanding how AI is being used across the organization
  • Security & Compliance: Maintaining enterprise security standards
  • Reliability: Ensuring consistent service across all users

Portkey adds a comprehensive governance layer to address these enterprise needs. Let’s implement these controls step by step.

Enterprise Implementation Guide

Portkey allows you to use 1600+ LLMs with your Agno AI agents setup, with minimal configuration required. Let’s set up the core components in Portkey that you’ll need for integration.

Enterprise Features Now Available

Agno AI agents now has:

  • Departmental budget controls
  • Model access governance
  • Usage tracking & attribution
  • Security guardrails
  • Reliability features

Frequently Asked Questions

Resources