Westenets/livekit-agents: A powerful framework for building realtime voice AI agents 🤖🎙️📹 · GitHub

from livekit.agents import (
    Agent,
    AgentServer,
    AgentSession,
    JobContext,
    RunContext,
    cli,
    function_tool,
    inference,
)
from livekit.plugins import silero


@function_tool
async def lookup_weather(
    context: RunContext,
    location: str,
):
    """Used to look up weather information."""

    return {"weather": "sunny", "temperature": 70}


server = AgentServer()


@server.rtc_session()
async def entrypoint(ctx: JobContext):
    session = AgentSession(
        vad=silero.VAD.load(),
        # any combination of STT, LLM, TTS, or realtime API can be used
        # this example shows LiveKit Inference, a unified API to access different models via LiveKit Cloud
        # to use model provider keys directly, replace with the following:
        # from livekit.plugins import deepgram, openai, cartesia
        # stt=deepgram.STT(model="nova-3"),
        # llm=openai.LLM(model="gpt-4.1-mini"),
        # tts=cartesia.TTS(model="sonic-3", voice="9626c31c-bec5-4cca-baa8-f8ba9e84c8bc"),
        stt=inference.STT("deepgram/nova-3", language="multi"),
        llm=inference.LLM("openai/gpt-4.1-mini"),
        tts=inference.TTS("cartesia/sonic-3", voice="9626c31c-bec5-4cca-baa8-f8ba9e84c8bc"),
    )

    agent = Agent(
        instructions="You are a friendly voice assistant built by LiveKit.",
        tools=[lookup_weather],
    )

    await session.start(agent=agent, room=ctx.room)
    await session.generate_reply(instructions="greet the user and ask about their day")


if __name__ == "__main__":
    cli.run_app(server)

...
class IntroAgent(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions=f"You are a story teller. Your goal is to gather a few pieces of information from the user to make the story personalized and engaging."
            "Ask the user for their name and where they are from"
        )

    async def on_enter(self):
        self.session.generate_reply(instructions="greet the user and gather information")

    @function_tool
    async def information_gathered(
        self,
        context: RunContext,
        name: str,
        location: str,
    ):
        """Called when the user has provided the information needed to make the story personalized and engaging.

        Args:
            name: The name of the user
            location: The location of the user
        """

        context.userdata.name = name
        context.userdata.location = location

        story_agent = StoryAgent(name, location)
        return story_agent, "Let's start the story!"


class StoryAgent(Agent):
    def __init__(self, name: str, location: str) -> None:
        super().__init__(
            instructions=f"You are a storyteller. Use the user's information in order to make the story personalized."
            f"The user's name is {name}, from {location}"
            # override the default model, switching to Realtime API from standard LLMs
            llm=openai.realtime.RealtimeModel(voice="echo"),
            chat_ctx=chat_ctx,
        )

    async def on_enter(self):
        self.session.generate_reply()


@server.rtc_session()
async def entrypoint(ctx: JobContext):
    userdata = StoryData()
    session = AgentSession[StoryData](
        vad=silero.VAD.load(),
        stt="deepgram/nova-3",
        llm="openai/gpt-4.1-mini",
        tts="cartesia/sonic-3:9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
        userdata=userdata,
    )

    await session.start(
        agent=IntroAgent(),
        room=ctx.room,
    )
...

@pytest.mark.asyncio
async def test_no_availability() -> None:
    llm = google.LLM()
    async AgentSession(llm=llm) as sess:
        await sess.start(MyAgent())
        result = await sess.run(
            user_input="Hello, I need to place an order."
        )
        result.expect.skip_next_event_if(type="message", role="assistant")
        result.expect.next_event().is_function_call(name="start_order")
        result.expect.next_event().is_function_call_output()
        await (
            result.expect.next_event()
            .is_message(role="assistant")
            .judge(llm, intent="assistant should be asking the user what they would like")
        )