pip install praisonaiagents

pip install praisonai

pip install "praisonai[claw]"
praisonai claw
# 访问 http://localhost:8082

pip install "praisonai[flow]"
praisonai flow
# 访问 http://localhost:7861

pip install "praisonai[ui]"
praisonai ui

# 核心 SDK
pip install praisonaiagents

# 或者完整安装
pip install praisonai

# 设置 API Key
export OPENAI_API_KEY="your-api-key"

from praisonaiagents import Agent

agent = Agent(instructions="You are a senior data analyst.")
agent.start("Analyze the top 3 tech trends of 2026 and format as a markdown table.")

from praisonaiagents import Agent, Agents

research_agent = Agent(instructions="Research about AI")
summarise_agent = Agent(instructions="Summarise research agent's findings")

agents = Agents(agents=[research_agent, summarise_agent])
agents.start()

from praisonaiagents import Agent, MCP

# stdio - 本地 NPX 服务器
agent = Agent(tools=MCP("npx @modelcontextprotocol/server-memory"))

# Streamable HTTP - 生产服务器
agent = Agent(tools=MCP("https://api.example.com/mcp"))

# WebSocket - 实时双向
agent = Agent(tools=MCP("wss://api.example.com/mcp", auth_token="token"))

# 带环境变量
agent = Agent(
    tools=MCP(
        command="npx",
        args=["-y", "@modelcontextprotocol/server-brave-search"],
        env={"BRAVE_API_KEY": "your-key"}
    )
)

from praisonaiagents import Agent

agent = Agent(instructions="You are a helpful AI assistant")
agent.start("Write a movie script about a robot in Mars")

from praisonaiagents import Agent, Agents

research_agent = Agent(instructions="Research about AI trends")
writer_agent = Agent(instructions="Write engaging content based on research")

research_team = Agents(agents=[research_agent, writer_agent])
research_team.start()

from praisonaiagents import Agent

agent = Agent(
    instructions="You are a research analyst",
    deep_research=True  # 启用深度研究
)
agent.start("Research the impact of AI on healthcare in 2026")

from praisonaiagents import Agent, tool

@tool
def search(query: str) -> str:
    """Search the web for information."""
    return f"Results for: {query}"

@tool
def calculate(expression: str) -> float:
    """Evaluate a math expression."""
    return eval(expression)

agent = Agent(
    instructions="You are a helpful assistant",
    tools=[search, calculate]
)

agent.start("Search for AI news and calculate 15*4")

from praisonaiagents import Agent

agent = Agent(
    name="Assistant",
    memory=True  # 启用记忆
)

agent.chat("Hello!")  # 自动保存
agent.chat("What did I say earlier?")  # 回忆

# 添加知识
praisonai knowledge add ./docs

# 查询知识
praisonai knowledge query "How to use the API"

# 列出知识
praisonai knowledge list

from praisonaiagents import Agent, db

agent = Agent(
    name="Assistant",
    db=db(database_url="postgresql://localhost/mydb"),
    session_id="my-session"
)

agent.chat("Hello!")  # 自动持久化消息、运行、追踪

framework: praisonai
topic: "Write a blog post about AI"

agents:
  researcher:
    role: Research Analyst
    goal: Research AI trends and gather information
    instructions: "Find accurate information about AI trends"

  writer:
    role: Content Writer
    goal: Write engaging blog posts
    instructions: "Write clear, engaging content based on research"

praisonai agents.yaml

from praisonaiagents import Agent

agent = Agent(
    instructions="You are a planning assistant",
    planning=True  # 启用计划模式
)

# Agent 会：plan → execute → reason → plan → execute → ...
agent.start("Plan a product launch for our new AI product")

praisonai --planning
praisonai --planning-tools
praisonai --planning-reasoning

from praisonaiagents import Agent, Guardrails

guardrails = Guardrails(
    input_validator=lambda x: x if len(x) < 1000 else x[:1000],
    output_validator=lambda x: x if "safe" in x.lower() else "[FILTERED]"
)

agent = Agent(
    instructions="You are a helpful assistant",
    guardrails=guardrails
)

from praisonaiagents import Agent

# 使用 OpenAI
agent = Agent(model="gpt-4", instructions="...")

# 使用 Anthropic
agent = Agent(model="claude-3-5-sonnet-20241022", instructions="...")

# 使用 Gemini
agent = Agent(model="gemini-pro", instructions="...")

# 使用本地 Ollama
agent = Agent(model="ollama/llama3", instructions="...")

from praisonaiagents import Agent

researcher = Agent(
    instructions="You are a research analyst. Research the top 3 AI trends of 2026.",
    deep_research=True
)
researcher.start()

from praisonaiagents import Agent

support = Agent(
    instructions="You are a helpful customer support agent.",
    memory=True,
    tools=["web_search", "knowledge_base"]
)
support.start()

from praisonaiagents import Agent

coder = Agent(
    instructions="You are an expert Python developer.",
    tools=["file_read", "file_write", "code_execute"]
)
coder.start("Write a web scraper for news articles")

pip install "praisonai[langfuse]"
praisonai langfuse

pip install praisonaiagents

# 环境变量
export OPENAI_API_KEY="your-key"
export ANTHROPIC_API_KEY="your-key"

docker build -t praisonai .
docker run -p 8082:8082 praisonai

apiVersion: apps/v1
kind: Deployment
metadata:
  name: praisonai
spec:
  replicas: 3
  template:
    spec:
      containers:
      - name: praisonai
        image: praisonai:latest
        ports:
        - containerPort: 8082

# 克隆仓库
git clone https://github.com/MervinPraison/PraisonAI.git
cd PraisonAI

# 安装开发依赖
pip install -e ".[dev]"

# 运行测试
pytest

# 代码格式
ruff format .
ruff check .

# 创建分支
git checkout -b feature/new-feature

# 提交
git commit -m "feat: add new feature"

# 推送
git push origin feature/new-feature

# 创建 PR

pip install praisonaiagents

export OPENAI_API_KEY="your-api-key"

agent = Agent(model="ollama/llama3", instructions="...")

agent = Agent(db=db(database_url="postgresql://localhost/mydb"))