Agno Registry

Register and visualise your components in real-time on Agno Platform.

Register Your Components

In Agno you create Agents, Teams, Workflows, and Apps. These are collectively referred to as “Components of your Agentic System”. When you run any of the above components, it is automatically registered and monitored out of the box. This means you can instantly view them, along with their metadata and configuration, in the Agno Registry.

The Registry acts as a unified dashboard where all your Agno Agents, Teams, Workflows and Apps are displayed, giving you full visibility into your operational environment. No additional setup is required.

Start exploring at app.agno.com/registry.

Authenticate & Enable Monitoring

1. Authenticate using CLI or API key

   To log agent sessions, you need to authenticate using one of these methods:

   Method A: Log in using your command line interface

   ag setup
   

   Method B: Log using an API key

   Get your API key from Agno App and use it to connect your agents to the Agno Platform.

   export AGNO_API_KEY=your_api_key_here
   

2. Enable Monitoring

   After authentication, enable monitoring for a particular agent or globally for all agents.

   Method A: For a Specific Agent

   agent = Agent(markdown=True, monitoring=True)
   

   Method B: Globally via Environment Variable

   export AGNO_MONITOR=true
   

3. Register Your Component

   Once monitoring is enabled, you can run your agent/team/workflow/app and view it in the registry:

   1. Create a file agent.py with this sample code:

   agent.py

   from agno.agent import Agent
   from agno.embedder.openai import OpenAIEmbedder
   from agno.knowledge.url import UrlKnowledge
   from agno.models.openai import OpenAIChat
   from agno.tools.reasoning import ReasoningTools
   from agno.memory.v2.db.sqlite import SqliteMemoryDb
   from agno.memory.v2.memory import Memory
   from agno.vectordb.lancedb import LanceDb, SearchType
   from agno.storage.sqlite import SqliteStorage
   
   memory = Memory(
       db=SqliteMemoryDb(table_name="memory", db_file="tmp/memory.db"),
       model=OpenAIChat(id="gpt-4o-mini"),
   )
   # Load Agno documentation in a knowledge base
   knowledge = UrlKnowledge(
       urls=["https://docs.agno.com/introduction/agents.md"],
       vector_db=LanceDb(
           uri="tmp/lancedb",
           table_name="agno_docs",
           search_type=SearchType.hybrid,
           # Use OpenAI for embeddings
           embedder=OpenAIEmbedder(id="text-embedding-3-small", dimensions=1536),
       ),
   )
   
   agent = Agent(
       name="Agno Assist",
       description="You can answer questions from the agno documentation",
       agent_id="agno-assist",
       model=OpenAIChat(id="gpt-4o-mini"),
       storage=SqliteStorage(table_name="agent_sessions", db_file="tmp/agents.db"),
       memory=memory,
       enable_agentic_memory=True,
       instructions=[
           "Use tables to display data.",
           "Include sources in your response.",
           "Search your knowledge before answering the question.",
           "Only include the output in your response. No other text.",
       ],
       knowledge=knowledge,
       tools=[ReasoningTools(add_instructions=True)],
       add_datetime_to_instructions=True,
       markdown=True,
   )
   
   if __name__ == "__main__":
       # Load the knowledge base, comment out after first run
       # Set recreate to True to recreate the knowledge base if needed
       agent.knowledge.load(recreate=False)
       agent.print_response(
           "What are Agents?",
           stream=True,
           show_full_reasoning=True,
           stream_intermediate_steps=True,
       )
   

   2. Run your code locally
   3. View your agent at app.agno.com/registry

   4. You can also check your agent configuration

Applications

You can register any application simply by running it — it will be monitored and visible on the platform automatically where you can view and interact with each component’s configuration in detail.

Additionally Playground apps can be opened and explored in the Agno Playground.

Learn more about the different types of applications.

Facing issues? Check out our troubleshooting guide