Skip to main content
The Agno SDK gives you three primitives: Agent, Team, Workflow, and a host of capabilities to turn them into production systems. 
from agno.agent import Agent
from agno.tools.yfinance import YFinanceTools

agent = Agent(
    name="Finance Agent",
    model="openai:gpt-5.4",
    tools=[YFinanceTools()],
    instructions="Fetch market data and produce a one-line take.",
)

agent.print_response("What's NVDA trading at today?")

​
Three primitives

PrimitiveUse it to
AgentBuild autonomous programs with a model, tools, and instructions.
TeamCoordinate multiple agents to achieve complex tasks.
WorkflowAchieve deterministic output using step-based execution.

​
Why the Agno SDK

  • Just Python. No DSL, no YAML, no custom language to learn.
  • Fast. Agents instantiate in microseconds with a minimal memory footprint. You’ll spin up one per request for isolation and permission scoping. Extreme performance is mandatory.
  • Agnostic. 30+ model providers, 100+ integrations, 20+ vector dbs, 10+ databases. Use any model provider, any database, any cloud provider.
  • Production-ready on day one. Sessions, memory, knowledge, tracing, evals, and human-in-the-loop come built in. The same agent you prototype in a python script serves real users behind AgentOS.
  • Three primitives. Agents for autonomy, teams for coordination, workflows for deterministic control. Compose them for your use case. Same SDK.

​
Capabilities

Turn Agents, Teams, and Workflows into production software.
CapabilityWhat it adds
Models30+ providers behind one API
Tools100+ integrations and the ability to write your own
MemoryPer-user and per-session memory
KnowledgeRAG over documents, URLs, and databases
LearningSelf-learning agents that improve over time
ReasoningBuilt-in chain-of-thought and reasoning agents
MultimodalImage, audio, and video input and output
Input & OutputPydantic-typed structured input and output
ContextAdd live context to every run
StatePer-agent, per-team, per-workflow state
DependenciesInject runtime values into prompts
SkillsReusable agent capabilities
HooksPre-run and post-run callbacks
GuardrailsValidate input and output
Human-in-the-LoopPause runs for approval, input, or external execution
DatabasePersist sessions, memory, knowledge, and traces
SessionsSession lifecycle and metrics
EvalsTest agent quality at scale
TracingOpenTelemetry tracing for every run

​
Where to start

Agents

Single autonomous programs with a model, tools, and instructions.

Teams

Coordinate multiple agents to achieve complex tasks.

Workflows

Achieve deterministic output using step-based execution.