Skip to main content

​
Why Agno?

Running multi-agent systems as a secure, scalable service is a hard, distributed systems problem. Most teams cobble together LLM calls, custom orchestration, and third-party monitoring tools. Agno replaces that patchwork with a unified platform:
LayerWhat it does
FrameworkBuild agents, teams, and workflows with memory, knowledge, guardrails, and 100+ integrations
AgentOS RuntimeServe your system in production with a stateless, secure FastAPI backend
Control PlaneTest, monitor, and manage your system using the AgentOS UI
AgentOS runs entirely in your cloud. No data leaves your environment, ideal for security-conscious teams.

​
Quick Example

Here’s an agent that connects to an MCP server, persists conversation state, and is served via FastAPI: 
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

agno_agent = Agent(
    name="Agno Agent",
    model=Claude(id="claude-sonnet-4-5"),
    db=SqliteDb(db_file="agno.db"),
    tools=[MCPTools(transport="streamable-http", url="https://docs.agno.com/mcp")],
    add_history_to_context=True,
    markdown=True,
)

agent_os = AgentOS(agents=[agno_agent])
app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="agno_agent:app", reload=True)
Run this script and connect to the AgentOS UI to chat with your agent:

​
Get Started

New to Agno? Follow the quickstart to build and deploy your first agent. Then explore the examples gallery for real-world applications.