LiveKit + MemorySync

Overview

Install livekit-memorysync and your LiveKit voice agent remembers callers across calls without ever sounding slow: recalled context is injected in on_user_turn_completed under a hard budget (default 1.2s) with the next recall prefetched in the background, so the common case is a zero-network cache hit. Both sides of the conversation persist as items finalize — with interruption metadata and deterministic idempotency seeds — and the injected block is turn-only and capture-excluded, so recalled context never re-enters storage. Composable by design: attach the engine to your own Agent subclass, or use the MemorySyncAgent drop-in. A memory outage degrades to "no memories this turn"; it can never stall or break a call.

Setup status and requirements

Supported version

livekit-memorysync 1.0.0 (PyPI)

Last setup review

2026-08-24

Permissions

A MemorySync API key with read and write scopes.

Limits

Requires livekit-agents 1.x (Python 3.10+). With speech-to-speech realtime models, prefer the memory search tool over turn injection — the turn boundary is synthesized from transcripts.

Capabilities

• Hard recall budget (default 1.2s) — tested against a 5s-slow backend
• Background prefetch: the common case is a zero-network cache hit
• Both-role capture with interruption metadata as items finalize
• Deterministic idempotency seeds — reconnects never duplicate memories
• Injection is turn-only and capture-excluded, by test
• Composition-first: keep your own Agent class (drop-in also available)
• Memory search function_tool for speech-to-speech realtime models
• livekit:: transcript scope — separate history, same shared memories

Quick Start

from livekit.agents import Agent, AgentSession
from livekit_memorysync import MemorySyncMemory

memory = MemorySyncMemory(api_key="ms_...", user_id="caller-42",
                          thread_id="room-123")

class Assistant(Agent):
    def __init__(self) -> None:
        super().__init__(instructions="You are a helpful voice assistant.")

    async def on_user_turn_completed(self, turn_ctx, new_message):
        await memory.on_user_turn(self, turn_ctx, new_message)

session = AgentSession(...)
memory.attach(session)   # capture both roles

Use Cases

Explore More