Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.agno.com/llms.txt

Use this file to discover all available pages before exploring further.

Agno is a python SDK for building multi-agent systems. It comes with three primitives (agents, teams and workflows) and a large set of capabilities you can attach to them (storage, memory, knowledge, learnings, compression). A primitive + capabilities becomes a component in your agent platform. Everything is pure Python. No new DSL to learn, no YAML to manage.

Primitives

PrimitiveDescription
AgentSimple autonomous programs with a model, tools, and instructions
TeamMultiple agents working together as a team
WorkflowStep-based workflow orchestration for deterministic output

Capabilities

Model and tools

CapabilityWhat it adds
Models30+ providers behind one API
Tools100+ integrations and the ability to write your own
SkillsComposable abilities you can attach to agents and teams
MultimodalImage, audio, and video input and output
Structured I/OType-safe input and output with Pydantic schemas

Memory and context

CapabilityWhat it adds
StorageDurability and persistence on any database
SessionsMulti-turn session management with summaries, history, and metrics
StateSession and agentic state agents can read and update mid-run
MemoryPer-user and per-session memory
KnowledgeSearch over documents, URLs, and databases
LearningAgents that improve over time with learned behavior and decisions
CompressionKeep long sessions inside the model’s context window
Context ProvidersInject live data from Calendar, Gmail, Drive, GitHub, Slack, MCP, and more

Control and safety

CapabilityWhat it adds
GuardrailsValidate input and output
HooksLifecycle hooks for input, output, and state
Human-in-the-LoopPause runs for approval, input, or external execution

Operations

CapabilityWhat it adds
Background executionLong-running runs that don’t block your API
EvalsMeasure accuracy, performance, and reliability; agent-as-judge
ObservabilityTracing with Langfuse, Logfire, Arize, and 12+ providers
SchedulerRun agents on a recurring schedule

Components

A primitive + capabilities + configuration becomes a live component of your agent platform. Components are the building blocks of your agent platform. You can create components in code, through a no-code UI or via the AgentOS API. Components created in code are final. Components created via the API or no-code UI can be versioned, checkpointed and reverted as needed. The /components API lets you build, version, and operate components over HTTP.

Versioned components

When components are created via the API, they carry a versioned configuration. Published versions are immutable, and each gets its own endpoint so you can pin clients to a specific version. A current pointer decides which version your production API serves: set it to a newer version to promote, or an earlier one to roll back. This is what makes a platform manageable at scale. Tune a component’s instructions, swap its model, or adjust its tools, ship it as a new version, and roll back in one call if it regresses. Versioned configs are also the foundation for an improvement loop: measure a component in production, propose a new config, publish it, and promote or roll back based on results.

Learn more

SDK Introduction

Get started with the Agent SDK.

Build Agents

Build Agents using the Agent SDK.

Build Agent Platform

Build an Agent Platform using the Agent SDK.