Skip to main content

What is Agno?

Agno is the runtime for agentic software. Build agents, teams, and workflows. Run them as scalable services. Monitor and manage them in production.

Framework

Build agents, teams, and workflows with memory, knowledge, guardrails, and 100+ integrations

Runtime

Serve your system in production with a stateless, session-scoped FastAPI backend

Control Plane

Test, monitor, and manage your system using the AgentOS UI

Key Features

Production-Ready Architecture

Agno runs in your infrastructure, not ours:
  • Stateless, horizontally scalable runtime - Scale to handle millions of users
  • Per-user and per-session isolation - Each user gets their own isolated context
  • 50+ APIs and background execution - REST, WebSocket, scheduled tasks, and more
  • Native tracing and full auditability - Every action is logged and traceable
  • Your data, your rules - Sessions, memory, knowledge, and traces stored in your database

Built for the New Software Paradigm

Agentic software introduces three fundamental shifts:

1. A New Interaction Model

Traditional software receives a request and returns a response. Agents stream reasoning, tool calls, and results in real time. They can pause mid-execution, wait for approval, and resume later. Agno treats streaming and long-running execution as first-class behavior.

2. A New Governance Model

Traditional systems execute predefined decision logic. Agents choose actions dynamically. Some actions are low risk. Some require user approval. Some require administrative authority. Agno lets you define who decides what as part of the agent definition:
  • Approval workflows
  • Human-in-the-loop
  • Audit logs
  • Enforcement at runtime

3. A New Trust Model

Traditional systems are designed to be predictable. Every execution path is defined in advance. Agents introduce probabilistic reasoning into the execution path. Agno builds trust into the engine itself:
  • Guardrails run as part of execution
  • Evaluations integrate into the agent loop
  • Traces and audit logs are first-class

What You Can Build

Agno powers real agentic systems built from the same primitives:

Pal

A personal agent that learns your preferences

Dash

A self-learning data agent grounded in six layers of context

Scout

A self-learning context agent that manages enterprise knowledge

Gcode

A post-IDE coding agent that improves over time

Investment Team

A multi-agent investment committee that debates and allocates capital
Single agents. Coordinated teams. Structured workflows. All built on one architecture.

Who Should Use Agno?

For Developers

If you’re building agentic applications, Agno provides:
  • A complete framework with batteries included
  • Production-ready infrastructure out of the box
  • 100+ integrations with LLM providers, tools, and databases
  • Real working examples in the cookbook

For Teams

If you’re shipping agentic software to production, Agno gives you:
  • Horizontally scalable architecture
  • Multi-tenancy with per-user isolation
  • Full observability and audit logs
  • Control over data and governance

For Enterprises

If you need enterprise-grade agentic systems, Agno offers:
  • Self-hosted deployment
  • Fine-grained access controls
  • Approval workflows and compliance
  • Integration with existing infrastructure

Next Steps

Quickstart

Build and run your first agent in under 5 minutes

Installation

Install Agno and set up your environment

Core Concepts

Understand the fundamental building blocks

Cookbook

Explore working examples and patterns

Build docs developers (and LLMs) love