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.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.
Primitives
Capabilities
Model and tools
| Capability | What it adds |
|---|---|
| Models | 30+ providers behind one API |
| Tools | 100+ integrations and the ability to write your own |
| Skills | Composable abilities you can attach to agents and teams |
| Multimodal | Image, audio, and video input and output |
| Structured I/O | Type-safe input and output with Pydantic schemas |
Memory and context
| Capability | What it adds |
|---|---|
| Storage | Durability and persistence on any database |
| Sessions | Multi-turn session management with summaries, history, and metrics |
| State | Session and agentic state agents can read and update mid-run |
| Memory | Per-user and per-session memory |
| Knowledge | Search over documents, URLs, and databases |
| Learning | Agents that improve over time with learned behavior and decisions |
| Compression | Keep long sessions inside the model’s context window |
| Context Providers | Inject live data from Calendar, Gmail, Drive, GitHub, Slack, MCP, and more |
Control and safety
| Capability | What it adds |
|---|---|
| Guardrails | Validate input and output |
| Hooks | Lifecycle hooks for input, output, and state |
| Human-in-the-Loop | Pause runs for approval, input, or external execution |
Operations
| Capability | What it adds |
|---|---|
| Background execution | Long-running runs that don’t block your API |
| Evals | Measure accuracy, performance, and reliability; agent-as-judge |
| Observability | Tracing with Langfuse, Logfire, Arize, and 12+ providers |
| Scheduler | Run 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. Acurrent 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.