Home/Documentation
Voice MemoryBeta

MemoAir Voice Memory

Drop-in persistent memory for voice agents. Targets <20ms local recall, cross-session continuity, per-user isolation, and an SDK-managed runtime pool — ships with a first-class LiveKit integration and a framework-neutral custom-agent pattern.

v0.3.2: memoair-voice now ships on npm for Node/TypeScript agents and PyPI for Python. Both use per-call user={id,name,metadata} routing through a bounded local runtime pool. LiveKit has drop-in adapters for Python and TypeScript; Pipecat, Vapi, and Retell use the custom-agent pattern until dedicated adapters land.

Start here

5-minute Quickstart
Install the SDK, grab keys from the dashboard, and call search_memory from any LLM. The local runtime is bundled — no Docker.
Concepts
The four retrieval lanes, plus v2 memory kinds (episodic, procedural, strategy, open-loops) and the automatic recall behaviors built on top.
Integrations
LiveKit is available now. Pipecat, Vapi, and Retell use the custom-agent pattern in v0.3.1.
Multi-workspace SaaS
Run voice agents for multiple tenants with per-client and per-end-user memory isolation.
SDK References
MemoAirVoiceClient, MemoAirLiveKitAgent, tools, and result types for Python and TypeScript.
HTTP API Reference
Loopback runtime wire contract — health, session lifecycle, search_memory, turn/after.

What you get

  • Local-first recall. Every search_memory call completes on-host. No network hop on the audio path.
  • Cross-session continuity. Permanent facts extracted from prior calls land back on disk before the next call starts.
  • Typed memory + automatic recall (v2). Episodes ("what did I do last month"), resurfaced open loops, replayable how-tos, learned tool-use guidance, referent resolution and a "what changed" changelog — all assembled inside one search_memory call, no extra wiring.
  • Per-user isolation by construction. The SDK pool spawns and reuses one local runtime per (project, user) while keeping a hard cap on warm processes.
  • LiveKit drop-in + custom framework path. Install memoair-livekit for the drop-in MemoAirLiveKitAgent. Non-LiveKit frameworks use MemoAirVoiceClient directly with per-call user={...}.