> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agno SDK

> Build your agent platform using the Agno SDK.

Agno is a Python SDK for building agent platforms. It gives you three primitives (agents, teams and workflows) and a large set of capabilities you can attach to them.

```python Agent theme={null}
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.tools.workspace import Workspace

workbench = Agent(
    name="Workbench",
    model="openai:gpt-5.5",
    db=SqliteDb(db_file="workbench.db"),
    tools=[Workspace(".")],
    enable_agentic_memory=True,
    add_history_to_context=True,
    num_history_runs=3,
    markdown=True,
)

workbench.print_response("Inventory this folder.")
```

```python Team theme={null}
from agno.agent import Agent
from agno.team import Team
from agno.tools.yfinance import YFinanceTools

bull = Agent(
    name="Bull",
    model="openai:gpt-5.4",
    role="Make the case FOR investing.",
    tools=[YFinanceTools()],
)
bear = Agent(
    name="Bear",
    model="openai:gpt-5.4",
    role="Make the case AGAINST investing.",
    tools=[YFinanceTools()],
)

team = Team(
    name="Investment Committee",
    members=[bull, bear],
    instructions="Hear both sides, then synthesize a balanced recommendation.",
)

team.print_response("Should I invest in NVIDIA?")
```

```python Workflow theme={null}
from agno.agent import Agent
from agno.team import Team
from agno.tools.yfinance import YFinanceTools
from agno.workflow import Step, Workflow

researcher = Agent(
    model="openai:gpt-5.4",
    tools=[YFinanceTools()],
    instructions="Gather raw market data.",
)

bull = Agent(model="openai:gpt-5.4", role="Make the case FOR investing.")
bear = Agent(model="openai:gpt-5.4", role="Make the case AGAINST investing.")
committee = Team(
    name="Investment Committee",
    members=[bull, bear],
    instructions="Debate the position.",
)

writer = Agent(
    model="openai:gpt-5.4",
    instructions="Write a 200-word investment brief.",
)

workflow = Workflow(
    name="Stock Research",
    steps=[
        Step(name="Research", agent=researcher),
        Step(name="Debate", team=committee),
        Step(name="Report", agent=writer),
    ],
)

workflow.print_response("Analyze NVIDIA for investment.")
```

## Choose the right primitive

| Primitive | Use it when | What Agno handles |
| - | - | - |
| [Agent](https://agno-v2.mintlify.site/agents/overview.md) | One model-driven program can own the task | Context, tool calls, sessions, memory, knowledge, and guardrails |
| [Team](https://agno-v2.mintlify.site/teams/overview.md) | The task benefits from specialist roles or dynamic delegation | Coordination, routing, broadcast, task lists, and nested teams |
| [Workflow](https://agno-v2.mintlify.site/workflows/overview.md) | The process needs repeatable steps, branches, loops, or parallel work | Control flow across agents, teams, functions, and nested workflows |

## Add what your use case needs

### Model and tools

| Capability | What it adds |
| - | - |
| [Models](https://agno-v2.mintlify.site/models/overview.md) | 30+ providers behind one API |
| [Tools](https://agno-v2.mintlify.site/tools/overview.md) | 100+ integrations and the ability to write your own |
| [Skills](https://agno-v2.mintlify.site/skills/overview.md) | Composable abilities you attach to agents and teams |
| [Multimodal](https://agno-v2.mintlify.site/multimodal/overview.md) | Image, audio, and video input and output |
| [Structured I/O](https://agno-v2.mintlify.site/input-output/overview.md) | Type-safe input and output with Pydantic schemas |

### Memory and context

| Capability | What it adds |
| - | - |
| [Storage](https://agno-v2.mintlify.site/database/overview.md) | Session and application data in a supported database |
| [Sessions](https://agno-v2.mintlify.site/sessions/overview.md) | Multi-turn sessions with summaries, history, and metrics |
| [State](https://agno-v2.mintlify.site/state/overview.md) | State your agents can read and update mid-run |
| [Memory](https://agno-v2.mintlify.site/memory/overview.md) | Persistent user facts and preferences |
| [Knowledge](https://agno-v2.mintlify.site/knowledge/overview.md) | Search over documents, URLs, and databases |
| [Learning](https://agno-v2.mintlify.site/learning/overview.md) | Agents that improve over time from feedback and outcomes |
| [Compression](https://agno-v2.mintlify.site/compression/overview.md) | Keep long sessions inside the model's context window |
| [Context Providers](https://agno-v2.mintlify.site/context-providers/overview.md) | Inject live data from Calendar, Gmail, Drive, GitHub, Slack, MCP |
| [Dependencies](https://agno-v2.mintlify.site/dependencies/overview.md) | Inject runtime values into prompts |

### Control and safety

| Capability | What it adds |
| - | - |
| [Guardrails](https://agno-v2.mintlify.site/guardrails/overview.md) | Validate input and output |
| [Hooks](https://agno-v2.mintlify.site/hooks/overview.md) | Pre-run and post-run callbacks |
| [Human-in-the-Loop](https://agno-v2.mintlify.site/hitl/overview.md) | Pause runs for approval, input, or external execution |

### Operations

| Capability | What it adds |
| - | - |
| [Background execution](https://agno-v2.mintlify.site/background-execution/overview.md) | Long-running runs that don't block your API |
| [Evals](https://agno-v2.mintlify.site/evals/overview.md) | Measure accuracy, performance, and reliability |
| [Observability](https://agno-v2.mintlify.site/observability/overview.md) | OpenTelemetry tracing into your own database |
| [Scheduler](https://agno-v2.mintlify.site/scheduler/overview.md) | Run agents and workflows on a recurring schedule |

## From SDK to platform

Register the same agents, teams, and workflows with AgentOS to run them behind a FastAPI application. AgentOS provides REST APIs and runtime support for persistence, authorization, tracing, background execution, scheduling, and interfaces.

## Where to start

> **[Build your first agent](https://agno-v2.mintlify.site/sdk/setup.md)**
>
> Install Agno, configure a model, and run an agent locally.

> **[Run on AgentOS](https://agno-v2.mintlify.site/agent-os/introduction.md)**
>
> Serve your agents, teams, and workflows through an API.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.