memoair-livekit 0.2.1

LiveKit Agent integration for MemoAir voice memory

memoair-livekit

LiveKit Agent integration for MemoAir voice memory. Drop-in livekit.agents.Agent subclass that searches memory before every LLM turn and persists each completed turn.

Install

pip install memoair-livekit

Quick start

import asyncio
from livekit.agents import AgentSession
from memoair_livekit import MemoAirVoiceAgent

async def entrypoint(ctx):
    agent = MemoAirVoiceAgent(
        api_key="mka_...",
        project_id="proj_123",
        user_id=ctx.room.local_participant.identity,
        instructions="You are a helpful voice assistant.",
    )
    session = AgentSession(vad=..., stt=..., llm=..., tts=...)

    # Required: LiveKit's base Agent does NOT call on_agent_response_completed.
    # Without this wiring, search runs every turn but nothing is saved.
    @session.on("conversation_item_added")
    def _on_item_added(event):
        if event.item.role == "assistant":
            asyncio.create_task(
                agent.on_agent_response_completed(session.chat_ctx, event.item)
            )

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

Full docs: https://docs.memoair.dev/voice/integrations/livekit