agno agent 的开发与其他框架没太多区别，以下简单说明下

基本流程

• agent

包含功能工具的

def get_tools(run_context: RunContext):
    role = (run_context.session_state or {}).get("role", "general")
    if role == "finance":
        return [YFinanceTools()]
    return [DuckDuckGoTools()]


agent = Agent(
    model=OpenAIResponses(id="gpt-5-mini"),
    tools=get_tools,
)

• agent + skills

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    skills=Skills(loaders=[LocalSkills("/path/to/skills")]),
    instructions=[
        "You have access to specialized skills.",
        "Use get_skill_instructions to load full guidance when needed.",
    ],
)

• WorkflowAgent

新出的模式

from agno.workflow import WorkflowAgent
from agno.workflow.workflow import Workflow
from agno.models.openai import OpenAIResponses

workflow_agent = WorkflowAgent(
    model=OpenAIResponses(id="gpt-5.2"),  # Set the model that should be used
    num_history_runs=4  # How many of the previous runs should it take into account
)

workflow = Workflow(
    name="Story Generation Workflow",
    description="A workflow that generates stories, formats them, and adds references",
    agent=workflow_agent,
)

• 知识库集成

knowledge = Knowledge(
    vector_db=ChromaDb(
        collection="docs",
        path="tmp/chromadb",
        persistent_client=True,
        search_type=SearchType.hybrid,
        embedder=GeminiEmbedder(id="gemini-embedding-001"),
    ),
)

# Load content into the knowledge base
knowledge.insert(url="https://docs.agno.com/introduction.md", skip_if_exists=True)

# Create an agent that searches the knowledge base
agent = Agent(
    model=Gemini(id="gemini-3-flash-preview"),
    knowledge=knowledge,
    search_knowledge=True,
    markdown=True,
)

• 记忆集成

db = PostgresDb(
  db_url=db_url,
  memory_table="user_memories",  # Optionally specify a table name for the memories
)


# Initialize Agent
memory_agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    # Give the Agent the ability to update memories
    enable_agentic_memory=True,
    # OR - Run the MemoryManager automatically after each response
    update_memory_on_run=True,
    markdown=True,
)

• mcp 集成

airbnb_tools = MCPTools(command="npx -y @openbnb/mcp-server-airbnb --ignore-robots-txt")
    google_maps_tools = MCPTools(command="npx -y @modelcontextprotocol/server-google-maps", env=env)
    await airbnb_tools.connect()
    await google_maps_tools.connect()

    try:
        agent = Agent(
            tools=[airbnb_tools, google_maps_tools],
            markdown=True,
        )

        await agent.aprint_response(message, stream=True)
    finally:
        await airbnb_tools.close()
        await google_maps_tools.close()

说明

以上是关于简单模式的说明，后续说明下啊team 模式的

参考资料

https://docs.agno.com/agents/building-agents