Multi-Agent Systems

from crewai import Agent, Task, Crew, Process
from crewai_tools import SerperDevTool

search_tool = SerperDevTool()

# Define agents with roles and backstories
researcher = Agent(
    role="Senior Research Analyst",
    goal="Find accurate, up-to-date information on any topic",
    backstory="You are an expert researcher with 10 years of experience...",
    tools=[search_tool],
    verbose=True
)

writer = Agent(
    role="Content Writer",
    goal="Write clear, engaging articles based on research",
    backstory="You transform complex research into readable content...",
    verbose=True
)

# Define tasks
research_task = Task(
    description="Research the current state of electric vehicles in 2024",
    expected_output="A detailed summary of EV market trends, key players, and statistics",
    agent=researcher
)

write_task = Task(
    description="Write a 500-word article using the research provided",
    expected_output="A polished, SEO-friendly article with clear sections",
    agent=writer,
    context=[research_task]  # Writer sees researcher's output
)

# Assemble and run the crew
crew = Crew(
    agents=[researcher, writer],
    tasks=[research_task, write_task],
    process=Process.sequential
)

result = crew.kickoff()
print(result)

import autogen

config_list = [{"model": "gpt-4o", "api_key": "YOUR_KEY"}]

# Assistant that can write and execute code
assistant = autogen.AssistantAgent(
    name="Assistant",
    llm_config={"config_list": config_list},
    system_message="You are a helpful AI. Write Python code to solve problems."
)

# Proxy for the human — can run code locally
user_proxy = autogen.UserProxyAgent(
    name="User",
    human_input_mode="NEVER",       # Fully automatic
    max_consecutive_auto_reply=5,
    code_execution_config={"work_dir": "coding", "use_docker": False},
    is_termination_msg=lambda x: "DONE" in x.get("content", "")
)

# Start the conversation
user_proxy.initiate_chat(
    assistant,
    message="Calculate the first 20 Fibonacci numbers and plot them."
)

from langgraph.graph import StateGraph, END
from typing import TypedDict, List

class AgentState(TypedDict):
    messages: List[str]
    next_agent: str
    final_output: str

# Define agent nodes
def supervisor(state: AgentState) -> AgentState:
    """Decides which agent to call next"""
    last_msg = state["messages"][-1]
    if "search" in last_msg.lower():
        return {**state, "next_agent": "researcher"}
    elif "write" in last_msg.lower():
        return {**state, "next_agent": "writer"}
    else:
        return {**state, "next_agent": END}

def researcher(state: AgentState) -> AgentState:
    # ... call search API, return results
    result = "Found: EV market grew 35% in 2024..."
    return {**state, "messages": state["messages"] + [result], "next_agent": "supervisor"}

def writer(state: AgentState) -> AgentState:
    # ... write based on research
    article = "The EV revolution is accelerating..."
    return {**state, "final_output": article, "next_agent": END}

# Build the graph
graph = StateGraph(AgentState)
graph.add_node("supervisor", supervisor)
graph.add_node("researcher", researcher)
graph.add_node("writer", writer)

graph.set_entry_point("supervisor")
graph.add_conditional_edges("supervisor", lambda s: s["next_agent"])
graph.add_edge("researcher", "supervisor")
graph.add_edge("writer", END)

app = graph.compile()
result = app.invoke({"messages": ["Write a report on EVs"], "next_agent": "supervisor", "final_output": ""})