Skip to main content
Agno comes with a exceptionally well-built debug mode that helps you understand the flow of execution and the intermediate steps. For example:
  • Inspect the messages sent to the model and the response it generates.
  • Trace intermediate steps and monitor metrics like token usage, execution time, etc.
  • Inspect tool calls, errors, and their results. This can help you identify issues with your tools.

​
Debug Mode

To enable debug mode:
  1. Set the debug_mode parameter on your agent, to enable it for all runs.
  2. Set the debug_mode parameter on the run method, to enable it for the current run.
  3. Set the AGNO_DEBUG environment variable to True, to enable debug mode for all agents.
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.hackernews import HackerNewsTools

agent = Agent(
    model=Claude(id="claude-sonnet-4-5"),
    tools=[HackerNewsTools()],
    instructions="Write a report on the topic. Output only the report.",
    markdown=True,
    debug_mode=True,
    # debug_level=2, # Uncomment to get more detailed logs
)

# Run agent and print response to the terminal
agent.print_response("Trending startups and products.")
You can set debug_level=2 to get even more detailed logs.
Here’s how it looks:

​
Interactive CLI

Agno also comes with a pre-built interactive CLI that runs your Agent as a command-line application. You can use this to test back-and-forth conversations with your agent: 
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.anthropic import Claude
from agno.tools.hackernews import HackerNewsTools

agent = Agent(
    model=Claude(id="claude-sonnet-4-5"),
    tools=[HackerNewsTools()],
    db=SqliteDb(db_file="tmp/data.db"),
    add_history_to_context=True,
    num_history_runs=3,
    markdown=True,
)

# Run agent as an interactive CLI app
agent.cli_app(stream=True)