agno

Agno 技能

使用 Agno 构建可用于生产环境的 AI Agent。Agno 是一个轻量、与模型无关的框架，支持 Agent、团队、工作流和 MCP 集成。

何时使用此技能

出现以下情况时，应触发此技能：

• 使用工具、记忆、结构化输出或知识构建 AI Agent
• 创建基于角色委派任务的多 Agent 团队
• 实现包含顺序、并行、条件或路由步骤的工作流
• 集成 MCP 服务（stdio、SSE 或 Streamable HTTP）
• 使用 AgentOS（基于 FastAPI 的运行时）部署 Agent
• 使用 LearningMachine（用户档案、实体记忆、会话上下文）
• 调试 Agent 行为或优化性能

架构概览

Agent          - Single autonomous AI unit (model + tools + instructions)
Team           - Multiple agents coordinated by a leader (route/broadcast/tasks modes)
Workflow       - Pipeline-based execution (Step, Parallel, Condition, Loop, Router)
AgentOS        - FastAPI runtime for deploying agents as production APIs
LearningMachine - Persistent learning across sessions (profiles, memory, knowledge)

快速参考

1. 使用工具的基础 Agent

from agno.agent import Agent
from agno.models.google import Gemini
from agno.tools.yfinance import YFinanceTools

agent = Agent(
    name="Finance Agent",
    model=Gemini(id="gemini-3-flash-preview"),
    tools=[YFinanceTools()],
    add_datetime_to_context=True,
    markdown=True,
)

agent.print_response("Give me a quick brief on NVIDIA", stream=True)

2. 使用 Pydantic 的结构化输出

from typing import List, Optional
from agno.agent import Agent
from agno.models.google import Gemini
from agno.tools.yfinance import YFinanceTools
from pydantic import BaseModel, Field

class StockAnalysis(BaseModel):
    ticker: str = Field(..., description="Stock ticker symbol")
    company_name: str = Field(..., description="Full company name")
    current_price: float = Field(..., description="Current price in USD")
    summary: str = Field(..., description="One-line summary")
    key_drivers: List[str] = Field(..., description="2-3 key growth drivers")
    recommendation: str = Field(..., description="Buy, Hold, or Sell")

agent = Agent(
    model=Gemini(id="gemini-3-flash-preview"),
    tools=[YFinanceTools()],
    output_schema=StockAnalysis,
)

response = agent.run("Analyze NVIDIA")
analysis: StockAnalysis = response.content
print(f"{analysis.company_name}: {analysis.recommendation}")

3. 使用存储的 Agent（会话持久化）

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.google import Gemini

agent = Agent(
    model=Gemini(id="gemini-3-flash-preview"),
    db=SqliteDb(db_file="tmp/agents.db"),
    add_history_to_context=True,
    num_history_runs=5,
    markdown=True,
)

# Same session_id = continuous conversation across runs
agent.print_response("Analyze NVDA", session_id="my-session", stream=True)
agent.print_response("Compare that to Tesla", session_id="my-session", stream=True)

4. 使用记忆的 Agent（用户偏好）

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.memory import MemoryManager
from agno.models.google import Gemini

db = SqliteDb(db_file="tmp/agents.db")

agent = Agent(
    model=Gemini(id="gemini-3-flash-preview"),
    db=db,
    memory_manager=MemoryManager(
        model=Gemini(id="gemini-3-flash-preview"),
        db=db,
    ),
    enable_agentic_memory=True,  # Agent decides when to store/recall
    markdown=True,
)

# Agent remembers user preferences across sessions
agent.print_response(
    "I'm interested in AI stocks. My risk tolerance is moderate.",
    user_id="[email protected]",
    stream=True,
)

5. 多 Agent 团队

from agno.agent import Agent
from agno.models.google import Gemini
from agno.team.team import Team
from agno.tools.yfinance import YFinanceTools

bull = Agent(
    name="Bull Analyst",
    role="Make the investment case FOR a stock",
    model=Gemini(id="gemini-3-flash-preview"),
    tools=[YFinanceTools()],
)

bear = Agent(
    name="Bear Analyst",
    role="Make the investment case AGAINST a stock",
    model=Gemini(id="gemini-3-flash-preview"),
    tools=[YFinanceTools()],
)

team = Team(
    name="Investment Research",
    model=Gemini(id="gemini-3-flash-preview"),
    members=[bull, bear],
    instructions=["Get both perspectives, then synthesize a balanced recommendation"],
    show_members_responses=True,
    markdown=True,
)

team.print_response("Should I invest in NVIDIA?", stream=True)

6. 顺序工作流

from agno.agent import Agent
from agno.models.google import Gemini
from agno.tools.yfinance import YFinanceTools
from agno.workflow import Step, Workflow

data_agent = Agent(name="Data Gatherer", model=Gemini(id="gemini-3-flash-preview"), tools=[YFinanceTools()])
analyst = Agent(name="Analyst", model=Gemini(id="gemini-3-flash-preview"))
writer = Agent(name="Report Writer", model=Gemini(id="gemini-3-flash-preview"), markdown=True)

workflow = Workflow(
    name="Research Pipeline",
    steps=[
        Step(name="Gather Data", agent=data_agent),
        Step(name="Analyze", agent=analyst),
        Step(name="Write Report", agent=writer),
    ],
)

workflow.print_response("Analyze NVIDIA for investment", stream=True)

7. MCP 服务集成（stdio）

import asyncio
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.mcp import MCPTools

async def run_agent(message: str) -> None:
    async with MCPTools(command="uvx mcp-server-git") as mcp_tools:
        agent = Agent(model=Claude(id="claude-sonnet-4-5-20250929"), tools=[mcp_tools])
        await agent.aprint_response(message, stream=True)

asyncio.run(run_agent("What is the license for this project?"))

8. MCP 服务（Streamable HTTP）

import asyncio
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.mcp import MCPTools

async def run_agent(message: str) -> None:
    async with MCPTools(
        transport="streamable-http",
        url="https://docs.agno.com/mcp",
    ) as mcp_tools:
        agent = Agent(model=Claude(id="claude-sonnet-4-5-20250929"), tools=[mcp_tools], markdown=True)
        await agent.aprint_response(message, stream=True)

asyncio.run(run_agent("What is Agno?"))

9. 多个 MCP 服务

import asyncio
from os import getenv
from agno.agent import Agent
from agno.tools.mcp import MultiMCPTools

async def run_agent(message: str) -> None:
    mcp_tools = MultiMCPTools(
        commands=["npx -y @openbnb/mcp-server-airbnb --ignore-robots-txt"],
        urls=["http://localhost:8000/mcp"],
        urls_transports=["streamable-http"],
        timeout_seconds=30,
    )
    await mcp_tools.connect()
    agent = Agent(tools=[mcp_tools], markdown=True)
    await agent.aprint_response(message, stream=True)
    await mcp_tools.close()

asyncio.run(run_agent("Find listings in Barcelona"))

10. LearningMachine（持久化学习）

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.learn import LearningMachine, LearningMode, UserProfileConfig
from agno.models.openai import OpenAIResponses

db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=LearningMachine(
        user_profile=UserProfileConfig(mode=LearningMode.ALWAYS),
    ),
    markdown=True,
)

agent.print_response("Hi! I'm Alice, call me Ali.", user_id="[email protected]", stream=True)
# Profile fields (name, preferred_name) captured automatically

关键模式

模式：MCP 连接生命周期

始终关闭 MCP 连接。使用异步上下文管理器或 try/finally：

# Preferred: context manager
async with MCPTools(command="uvx mcp-server-git") as tools:
    agent = Agent(tools=[tools])
    await agent.aprint_response("query")

# Alternative: manual lifecycle
tools = MCPTools(command="uvx mcp-server-git")
await tools.connect()
try:
    agent = Agent(tools=[tools])
    await agent.aprint_response("query")
finally:
    await tools.close()

模式：生产数据库（PostgreSQL）

from agno.db.postgres import PostgresDb
db = PostgresDb(db_url="postgresql+psycopg://user:pass@localhost:5432/agno")
agent = Agent(db=db, add_history_to_context=True)

模式：调试模式

agent = Agent(debug_mode=True)  # Detailed logs of messages, tools, tokens

模式：自定义工具

from agno.tools.decorator import tool

@tool
def get_weather(city: str) -> str:
    """Get current weather for a city."""
    return f"Weather in {city}: 72F, sunny"

agent = Agent(tools=[get_weather])

重要规则

• 切勿在循环中创建 Agent——为提升性能，应重复使用 Agent
• 对结构化响应使用 output_schema（不要使用自由格式解析）
• 生产环境使用 PostgreSQL，SQLite 仅用于开发
• 同步和异步均可用——所有公共方法都有对应的异步版本（以 a 为前缀）
• 始终关闭 MCP 连接——使用 try/finally 或异步上下文管理器
• 排查问题时启用 debug_mode=True

参考文件

详细文档见 references/：

• agents.md - Agent 参数、配置、工具、记忆、知识、护栏
• teams.md - 团队模式（route/broadcast/tasks）、成员协调
• workflows.md - 步骤类型（Step、Parallel、Condition、Loop、Router）
• mcp.md - MCP 集成（stdio、SSE、Streamable HTTP）、MultiMCPTools
• tools.md - 内置工具列表、自定义工具创建、工具钩子
• learning.md - LearningMachine 存储（profile、memory、session、knowledge、entity）
• models.md - 支持的模型提供商和配置

资源

• 文档：https://docs.agno.com
• GitHub：https://github.com/agno-agi/agno
• Cookbook 示例：https://github.com/agno-agi/agno/tree/main/cookbook
• 安装：pip install agno