from typing import TypedDict, Annotated
from langgraph.graph import add_messages

class AgentState(TypedDict, total=False):
    messages: Annotated[list, add_messages]  # Auto-merge
    next_agent: str  # For handoffs

from typing import TypedDict, Annotated, Dict, Any
from langchain_core.messages import BaseMessage
from langgraph.graph import add_messages

class AgentState(TypedDict, total=False):
    messages: Annotated[list[BaseMessage], add_messages]  # Auto-merge
    agent_type: str
    metadata: Dict[str, Any]
    next_agent: str  # For handoffs

undefined

**Deep dive:** `reference/base-agent-architecture.md`, `reference/cost-optimization.md`

from langgraph_supervisor import create_supervisor  # pip install langgraph-supervisor
from langgraph.prebuilt import create_react_agent

research_agent = create_react_agent(model, tools=research_tools, prompt="Research specialist")
writer_agent = create_react_agent(model, tools=writer_tools, prompt="Content writer")

supervisor = create_supervisor(agents=[research_agent, writer_agent], model=model)
result = supervisor.invoke({"messages": [("user", "Write article about LangGraph")]})

from langgraph_swarm import create_swarm, create_handoff_tool  # pip install langgraph-swarm

handoff_to_bob = create_handoff_tool(agent_name="Bob", description="Transfer for Python tasks")
alice = create_react_agent(model, tools=[query_db, handoff_to_bob], prompt="SQL expert")
bob = create_react_agent(model, tools=[execute_code], prompt="Python expert")

swarm = create_swarm(agents=[alice, bob], default_active_agent="Alice")

from langgraph.func import entrypoint, task
from langgraph.checkpoint.memory import InMemorySaver

@task
def research(query: str) -> str:
    return f"Results for: {query}"

@entrypoint(checkpointer=InMemorySaver())
def workflow(query: str) -> dict:
    result = research(query).result()
    return {"output": result}

from langchain_mcp_adapters.client import MultiServerMCPClient

async with MultiServerMCPClient(
    {"tools": {"transport": "stdio", "command": "python", "args": ["./mcp_server.py"]}}
) as client:
    tools = await client.get_tools()
    agent = create_react_agent(model, tools=tools)

from deep_agents import create_deep_agent
from deep_agents.backends import CompositeBackend, StateBackend, StoreBackend

backend = CompositeBackend({
    "/workspace/": StateBackend(),      # Ephemeral
    "/memories/": StoreBackend()        # Persistent
})
agent = create_deep_agent(
    model=ChatAnthropic(model="claude-opus-4-6"),
    backend=backend,
    interrupt_on=["deploy", "delete"],
    skills_dirs=["./skills/"]
)

undefined

**Deep dive:** `reference/guardrails.md` (input/output validation, tripwires, graph-node guardrails)

from lang_core import traced_agent, get_llm_for_task, LLMPriority
from lang_core.middleware import budget_enforcement_middleware

@traced_agent("QualificationAgent", tags=["sales"])
async def run_qualification(data):
    llm = get_llm_for_task(priority=LLMPriority.SPEED)
    # ... agent logic

{"ts":"[UTC ISO8601]","skill":"langgraph-agents","version":"2.0.0","variant":"default",
 "status":"[success|partial|error]","runtime_ms":[estimated ms from start],
 "metrics":{"agents_created":[n],"nodes_configured":[n],"graphs_built":[n]},
 "error":null,"session_id":"[YYYY-MM-DD]"}