Get Started
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.
Before running these examples, follow the SDK setup, then install the optional packages and set your model key:
uv pip install -U "agno[openai,sqlite]" yfinance
export OPENAI_API_KEY="your_openai_api_key"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.")Choose the right primitive
| Primitive | Use it when | What Agno handles |
|---|---|---|
| Agent | One model-driven program can own the task | Context, tool calls, sessions, memory, knowledge, and guardrails |
| Team | The task benefits from specialist roles or dynamic delegation | Coordination, routing, broadcast, task lists, and nested teams |
| Workflow | 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 | 30+ providers behind one API |
| Tools | 100+ integrations and the ability to write your own |
| Skills | Composable abilities you 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 | Session and application data in a supported database |
| Sessions | Multi-turn sessions with summaries, history, and metrics |
| State | State your agents can read and update mid-run |
| Memory | Persistent user facts and preferences |
| Knowledge | Search over documents, URLs, and databases |
| Learning | Agents that improve over time from feedback and outcomes |
| Compression | Reduce context usage in long sessions |
| Context Providers | Inject live data from Calendar, Gmail, Drive, GitHub, Slack, MCP |
| Dependencies | Inject runtime values into prompts |
Control and safety
| Capability | What it adds |
|---|---|
| Guardrails | Validate input and output |
| Hooks | Pre-run and post-run callbacks |
| 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 |
| Observability | OpenTelemetry tracing into your own database |
| Scheduler | 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.