Skip to main content
Agents are the core building block of Agno. An agent is an autonomous system powered by a language model that can use tools, remember context, and interact with knowledge bases.

​
What is an agent?

An agent combines:
  • A language model (OpenAI, Anthropic, Google, etc.)
  • Tools to take actions (web search, API calls, code execution)
  • Memory to remember user preferences and conversation history
  • Knowledge to ground responses in your documents
  • Instructions to define behavior and personality

​
Quick example

from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    name="Research Assistant",
    model=Claude(id="claude-sonnet-4-6"),
    tools=[DuckDuckGoTools()],
    instructions="You are a helpful research assistant. Always cite your sources."
)

response = agent.run("What are the latest developments in quantum computing?")
print(response.content)

​
Key capabilities

Tool calling

Give agents the ability to take actions and interact with external systems

Memory

Remember user preferences and conversation history across sessions

Knowledge

Ground responses in your documents with RAG

Instructions

Define agent behavior, personality, and constraints

​
Agent lifecycle

# 1. Create agent
agent = Agent(
    model=Claude(id="claude-sonnet-4-6"),
    tools=[YFinanceTools()]
)

# 2. Run agent
response = agent.run("What's the stock price of NVDA?")

# 3. Access results
print(response.content)
print(response.metrics)  # Token usage, latency, etc.

​
Next steps

Configuration

Learn about all agent parameters

API reference

Complete API documentation

Build docs developers (and LLMs) love

Get started for freeTalk to us